assignment gpt

Designing Assignments and Activities with ChatGPT and Generative AI in Mind

Generative AI, such as ChatGPT, can be a powerful tool to engage students in learning and creativity. Essentially, generative AI tools are those that create content on their own without human intervention. It can be useful for writing text, generating ideas, creating images, writing and editing code, and more. By designing assignments that incorporate generative AI technology, instructors can provide students with opportunities to explore, create, and problem-solve. However, as an instructor, you may also want to create assignments that challenge students to demonstrate their own knowledge and skills without relying heavily on AI-generated content. In this article, we will review different assignment ideas and strategies to create prompts and assignment ideas in different disciplines.

Table of Contents

Syllabus statements and student input, is ai use cheating.

• AI Detection
• Design Assignments to Limit AI Use
• Design Assignments to Work with AI
• Registration
• Recording from August, 2023
• Workshop Slides

Intelligent.com conducted a poll of more than 1,000 current college students in May 2023 regarding their use of ChatGPT for coursework. 30% of students used ChatGPT for coursework during the 2022/2023 academic year, and of that group, 46% utilized it frequently. Users of ChatGPT and other generative AI tools like Bing Chat and Google Bard continue to grow with some flattening of the upward trend in summer 2023. Generative AI is rapidly advancing and becoming more prevalent in education, work, and our daily lives. As an educator, it’s a good idea to help students be aware of the ethical considerations surrounding the use of generative AI.

• Consider adding an acceptable use statement in your syllabus. Here are some guidelines and examples.
• How do you think generative AI can be applied to the course assignments in this class?
• Can you share any specific examples of generative AI being used in educational settings?
• How can we ensure that AI tools are used in a way that promotes skill development in our course?
• After reviewing the assignment directions and grading information, what would be some helpful uses of AI tools that will still allow you to learn the content and demonstrate your learning?
• Based on various surveys and instructor experiences, not all students believe it is ethical to use AI on assignments. Be sure to include a discussion/policy about how AI can or cannot be used in group work.

There is no standard for determining if AI use by students qualifies as plagiarism or cheating . There is also no consistent standard for citing or crediting work using an AI tool. It may be useful to check with your professional organizations and journals and share any of their policies with students. Currently, AI is part of retail and other business careers, education in personalized learning, systems that make recommendations, human resources decisions, healthcare, agriculture, gaming, marketing, finance, and more .

Organization and publication examples:

• RTDNA Journalism Association
• NIH Grants Peer Review Policy
• IEEE Journal Submission Policy

Citation Style Guidance:

• APA: How to Cite ChatGPT
• MLA: How Do I Cite Generative AI in MLA Style?
• Chicago Style Manual

It may be useful to reflect on how you define plagiarism and cheating and then help guide students to think about it. Review this image from Matt Miller @DitchThatTextbook to help guide your thinking.

No True Detection of AI is Possible

There is no “fool-proof” way to detect AI use in student projects, and there have been many stories published about false positives and negatives using various AI detectors.

At NC State University, we provide access to Turnitin, which has an AI detector if you would like to get some input on if students have used AI to craft their writing. That said, do not use Turnitin as sole evidence that a student has cheated or plagiarized. Please review the academic integrity guidance and policies from the Office of Student Conduct. Note that the Division of Academic and Student Affairs also encourages faculty to notify students if they plan on using Turnitin.

• Turnitin at NC State
• Turnitin AI Detection
• Article on AI detection issues with Turnitin

AI detection and AI detector workaround programs are regularly being created and released. Here are some common tools and videos guiding students and content creators on how to get around AI detection.

• AI Text Classifier by OpenAI
• AI Content Detector: Writer  
• AI Writing CheckWriter’s AI Content Detector
• Video: How to Not Get Caught Using ChatGPT at School
• Video: New Way to Bypass AI Detection

There are also some red flags you can look for in reviewing student work. It’s helpful (albeit difficult in large classes) if you know your students writing and can determine if an assignment does not fit their typical way or level of writing. What to look for:

• A factual error or made-up citation
• Missing required assignment data sources or article text
• “Too perfect” in terms of grammar and usage
• Overly formal, detached, or impersonal style/tone
• Predictable formations – -like a five-paragraph essay from middle school language arts
• The writing too directly and repetitively parallels the assignment directions

Note: Students who are good at prompt writing and provide context, follow-up questions, a voice for the AI, etc., may not produce writing that exhibits these flaws. You may also want to consider having a conversation with a student about their work and topic if you have concerns. ChatGPT-4 (a paid option) is significantly better at avoiding these style issues, and Bing Chat is powered by GPT-4 (free).

Designing Assignments to Limit AI Usage

There are ways to design assignments that can make generative AI use more difficult for students. However, as tools become more sophisticated, assignment revisions may not be enough to truly prevent students from using AI; however, these strategies are a good start.

Ask ChatGPT

Ask ChatGPT to provide assignment examples in your field that would be difficult for it to complete. Include context, specific learning outcomes, and more to get a more specific list of suggestions. Prompt Example:

• You are a professor for an introductory course in {subject area} at the college level. You are trying to design assignments that would be tricky for students to use AI to complete. What are some assignment ideas and topics within the field that would be difficult for Bard to complete successfully?
• You are a professor for a college statistics course. Students are expected to recognize and be able to explain the central role of variability in the field of statistics. They also must be able to find variability when interpreting data. What are some course assignments that students can complete to show they have met these objectives and that are difficult for ChatGPT to complete? Explain how the assignment will help students demonstrate their understanding and what makes it complicated for a generative AI tool like ChatGPT. See the results here!

Require Specific Data Sources to be Used in the Assignment

ChatGPT is not connected to the web. It’s a “pretrained” tool that has not been trained on information post-2021. So, incorporating specific texts into assignments can make things more difficult for ChatGPT. You can ask students to write and cite sources/text from specific articles or videos. You can also provide data sets that students must use in their work.

Google Version History

Require that students submit written work using Google Docs, Slides, Sheets, etc., and use version history to validate that the writing and input occurred over time vs. in large chunks suggesting that students may have copied and pasted from another source like ChatGPT. Students have also used time stamps in Google Docs version history to exonerate themselves from false positives picked up by AI detectors.

Incorporate Student Discussion and Collaboration

In-person student discussions that reference past class activities, readings done outside of class, previous lectures, and so on can be integrated into your course. Examples:

• Ask students in a chemistry course to compare and contrast two models that they read about for homework or that were shared in a recorded lecture. Ask students to come up with examples in class (or on a discussion board) with a partner based on the reading assignment.
• Use Perusall and set the auto-grading (ai-assisted) feature to highly weight active engagement time and getting responses. Manually grade and let students know that credit comes from their in-text conversations with each other.

Reflective Assignments

AI tools are not truly reflective and aren’t likely (even fictionally) to make good connections between course content and personal experience or learnings. Examples:

• Write a reflection on a time when you struggled with a {subject area} concept. What was the concept? How did you eventually understand it? What advice would you give to other students who are struggling with the same concept?
• Compare and contrast two different ways of solving a problem {in your content area}. What are the advantages and disadvantages of each method? When would you use one method over the other?

Real-World & Localized Connections in Assignments

Some AI tools are not connected to the internet and will not have an understanding of local references or the most recent sources. Others may not be able to draw connections that make sense to humans who understand those “smaller” contexts. For example, we asked Bard to write a short story set in a modern-day context in Raleigh, North Carolina on the NC State Campus and gave it some specific guidelines. In addition to writing a formulaic story , Bard regularly referenced “The Old Well” which is part of the UNC-Chapel Hill campus. Prompt example:

• Analyze the impact of a recent policy change {content-specific} or ask students to choose a policy change that has been implemented in the last year. Research the policy change and its implications for the economy. Write a report that includes the expected impact, strengths and weaknesses of the change, and recommendations for how the policy change could be improved.

Take Assignments through a Process

Asking students to complete an assignment with a process including steps like brainstorming, mapping, drafting, peer review, an interview, and a final product can make it difficult for them to find successful ways to use AI. It may be able to help students with sections of the assignment but not the entire product or process. You can also ask students process-oriented questions along the way. You can also include ambiguous questions or those that require positions on controversial topics. Examples:

• Compare your answers to your team’s answers. Discuss any differences.
• Explain the process you followed to arrive at your conclusion.
• Analyze the ethical implications of each step in the process and propose alternatives if necessary.
• Explain the long-term consequences of implementing this process and how they might evolve over time.
• Discuss the role of creativity and innovation in…
• Identify potential biases, assumptions, and problems that could arise and suggest methods to mitigate them.

Retrieval Practice Activities

Retrieval practice activities allow students to practice recalling information from class activities, lectures, readings, and so on. If specific to course content, AI would not be helpful in these activities (particularly if completed in person). More on retrieval practice .

Multi-Step with a Creative Component

Create projects in which students demonstrate their learning. Essentially find ways to ask them to take what they’ve learned, organize it, and make something with it. Examples:

• Short story writing in which students must use content information, specific vocabulary, and maybe even primary sources to craft a story.
• Ask students to create a comic strip based on a concept, vocabulary, a reading, etc.
• Students creating a public service announcement video to demonstrate learning

Blended Instruction or Flipping

You may also want to consider using blended or flipping formats for your course in order to limit AI use. In this model, students would learn content outside of class time and then use class time for the application of what they learned.

Designing Assignments to Work with AI

AI tools are likely to be used by students in future careers and likely in their coursework, so one approach is to incorporate the tools directly and intentionally into assignments and activities.

“Am I going to teach students to write or to write with AI tools like ChatGPT? Derek Bruff

Consider these assignment reflection questions from Derek Bruff’s article “Assignment Makeovers in the AI Age.”

• Why does this assignment make sense for this course?
• What are the specific learning objectives for this assignment?
• How might students use AI tools while working on this assignment?
• How might AI undercut the goals of this assignment? How could you mitigate this?
• How might AI enhance the assignment? Where would students need help figuring that out?
• Focus on the process. How could you make the assignment more meaningful for students or support them more in the work?

Consider these ideas for assignments that can work with AI tools:

• Use AI to generate multiple explanations for a concept and ask students to critique the AI-generated explanations. Ask them to cite/use specific course readings, notes from lectures, etc., in their critiques.
• Save time in reviewing student writing by asking them or requiring them first to get an AI review of their work, then reflect on the review, make edits, and then submit their final work.
• Include an AI tool in a “Think-Pair-Share” activity in class. Students pair with another person in class and then with an AI tool.
• Ask students to predict what responses they will get from AI to specific course content questions, problem sets, etc.
• Provide several responses from AI and ask students to make a better or different product using those drafts/responses. They might make a mind map from a narrative created by AI and then find three additional sources to support or expand on different sections of the mind map.
• Assign a peer teaching project in which students will teach a concept or review a concept for their peers. Encourage students to get help from AI with the content and in designing a short activity that can be done as part of the peer teaching. Make students responsible for answering questions from peers and instructors. Use any gaps to adjust your own teaching.
• Ask students to debate an AI tool — students on one side and ChatGPT on the other.
• Ask students to find evidence for an AI-created “main points” of an article. First, copy and paste an article into ChatGPT (or a link to an article into Bing or Bard) and ask the tool to summarize the key points of the article. Then provide that to students and ask them to find quotes or details that expand on each point.

NC State Office of Faculty Excellence: Navigating the Landscape of Higher Education in the Age of Artificial Intelligence

Writing Instructors –> Tim Laquintano, Carly Schnitzler, and Annette Vee — TextGenEd: An Introduction to Teaching With Text Generation Technologies (Assignment examples for AI Literacy, Creative Explorations, Ethical Considerations, and more – access at the bottom of the article)

Writing Instructors –> Anna Mills (Curator). AI Text Generators and Teaching Writing: Starting Points For Inquiry

AI Writing Detection: Red Flags

Ethan & Lilach Mollick — Using AI to Implement Effective Teaching Strategies in Classrooms: Five Strategies, Including Prompts

Ethan Mollick — Assigning AI: Seven Ways of Using AI in Class and The Homework Apocalypse  

Jeffrey Young — EdSurge Instructors Rush to Do ‘Assignment Makeovers’ to Respond to ChatGPT” 

Derek Bruff

• Assignment Makeovers in the AI Age: Essay Edition
• Assignment Makeovers in the AI Age: Reading Response Edition

Tyler Cowen & Alexander Tabarook How to Learn & Teach Economics with Large Language Models, Including GPT

Sam Lau & Philip Guo Teaching Programming in the Age of ChatGPT – O’Reilly  

AI Prompts for Teaching  

Impact Research: K-12 Teachers & Students ChatGPT Use

Torrey Trust — Essential Considerations for Addressing the Possibility of AI-Driven Cheating, Part 1 | Faculty Focus  

Ideas to Limit AI Use in Assignments from Google Bard  

Educause Review: Artificial Intelligence

An introduction to prompting generative AI like ChatGPT for teaching and learning  

ChatGPT, Chatbots and Artificial Intelligence in Education – Ditch That Textbook

Artificial Intelligence and the Future of Teaching and Learning (PDF)  

Rethinking your Problem Sets in the World of Generative AI – MIT

Hybrid Teaching: Best Practices

Blended Learning | Columbia CTL  

How We Use AI to Enhance Your Writing | Grammarly 

30 AI tools for the classroom – Ditch That Textbook  

College of Education ChatGPT Resources

Have a thesis expert improve your writing

Check your thesis for plagiarism in 10 minutes, generate your apa citations for free.

• Knowledge Base

Using AI tools

• Using ChatGPT for Assignments | Tips & Examples

Using ChatGPT for Assignments | Tips & Examples

Published on 13 February 2023 by Jack Caulfield and Tobias Solis. Revised on 15 May 2023.

People are still figuring out the best use cases for ChatGPT , the popular chatbot based on a powerful AI language model. This article provides some ideas for how to use the tool to assist with your academic writing .

ChatGPT can assist you with the following steps when writing a paper, thesis , or dissertation :

• Developing a research question
• Creating an outline
• Generating literature ideas

Paraphrasing text

• Getting feedback

Instantly correct all language mistakes in your text

Be assured that you'll submit flawless writing. Upload your document to correct all your mistakes.

Table of contents

Developing a research question with chatgpt, creating an outline of your paper with chatgpt, generate literature ideas, getting feedback from chatgpt, limitations of chatgpt, other interesting articles, frequently asked questions about using chatgpt for assignments.

You can use ChatGPT to help you formulate a clear and concise research question by generating and improving potential questions.

With the help of ChatGPT, you can develop a large number of possible research questions within a short time. This is a great way to generate ideas and different approaches to a topic.

However, make sure that the generated questions make sense and meet your needs. As you can see from our example, you can keep working with ChatGPT to adapt its suggestions to your needs (or just edit the text directly if you already have a clear idea of what you want).

First input

Develop three possible research questions on the following topic: “The influence of social media on political opinion formation.”

ChatGPT output

• To what extent does exposure to diverse political perspectives on social media affect individuals’ political opinions and behaviours?
• How does the personalised algorithm of social media platforms shape the formation of political opinions among its users?
• What are the underlying factors that determine the effect of social media on political opinion formation, and how can they be measured and analysed?

Second input

Based on the second research question, develop three further research questions on the topic of polarisation in UK politics.

• Build my scientific method, qualitative discourse analysis, into each question
• Include the term “filter bubble” in each question
• How does the filter bubble effect on social media platforms contribute to the polarisation of political attitudes in the UK? A qualitative discourse analysis.
• What is the role of filter bubbles in perpetuating and reinforcing political echo chambers in the UK? A qualitative discourse analysis.
• How does the influence of filter bubbles on social media affect the ability of individuals to engage in productive political discourse across ideological divides in the UK? A qualitative discourse analysis.

Third input

Try to incorporate “qualitative discourse analysis” into the questions themselves, instead of using it as a separate sentence.

• How does a qualitative discourse analysis of filter bubble effect on social media platforms contribute to understanding the polarisation of political attitudes in the UK?
• What is the contribution of a qualitative discourse analysis to understanding the role of filter bubbles in perpetuating and reinforcing political echo chambers in the UK?
• How does a qualitative discourse analysis of the influence of filter bubbles on social media inform our understanding of the ability of individuals to engage in productive political discourse across ideological divides in the UK?

The only proofreading tool specialized in correcting academic writing

The academic proofreading tool has been trained on 1000s of academic texts and by native English editors. Making it the most accurate and reliable proofreading tool for students.

Correct my document today

You can also use ChatGPT to help you draft a research paper outline or thesis outline . To do this, try generating possible headings and subheadings and then improving them. ChatGPT can help to generate a clear and well-structured outline, especially if you keep adjusting the structure with its help.

However, it doesn’t have a deep understanding of your topic. As a result, inappropriate headings may sometimes be generated. It’s important to check that the outline makes sense and covers all the points needed to answer your research question.

You should also ensure that the headings and subheadings follow a logical structure. Scribbr’s Proofreading & Editing service can help you with this.

Create an outline for an academic research paper with the following research question:

“What is the contribution of a qualitative discourse analysis to understanding the role of filter bubbles in perpetuating and reinforcing political echo chambers in the US?”

The paper will be about 8 pages long.

• Background information on filter bubbles and political echo chambers
• Purpose of the study
• Research question
• Thesis statement
• Definition and concept of filter bubbles
• Definition and concept of political echo chambers
• Previous studies on the role of filter bubbles in perpetuating and reinforcing political echo chambers
• Critiques and limitations of previous studies
• Research design
• Participants
• Data collection and analysis
• Validity and reliability
• Findings from qualitative discourse analysis
• Results related to the research question
• Implications of the findings
• Interpretation of the results
• Comparison with previous studies
• Limitations of the study
• Implications for future research
• Summary of the results
• Implications for understanding the role of filter bubbles in perpetuating and reinforcing political echo chambers
• Conclusion and recommendations for future research
• List of references used in the paper
• Data collection materials
• Examples of qualitative data analysis

This seems like too much information to fit into only 8 pages. Can you condense the outline, for example removing the appendices and simplifying the structure?

• Background on filter bubbles and political echo chambers
• Definition of filter bubbles and political echo chambers
• Previous studies on the role of filter bubbles
• Limitations of previous studies
• Implications for understanding the role of filter bubbles
• Final thoughts

ChatGPT can be a useful way to generate ideas regarding what sources you might use in your work. Try asking it for suggestions about where to look and what to consider.

However, we advise against using it to find sources directly. It’s not designed for this and, if asked to do it, often just creates fake sources and presents them as real. Search a database like Google Scholar instead.

What types of sources could I use to write a paper on the following research question?

“What is the contribution of a qualitative discourse analysis to understanding the role of filter bubbles in perpetuating and reinforcing political echo chambers in the UK?”

When writing a paper on the contribution of qualitative discourse analysis to understanding the role of filter bubbles in perpetuating and reinforcing political echo chambers in the UK, you could use the following types of sources:

• Academic journals and articles: These are a good place to start when you’re looking for information on specific topics and they can provide you with in-depth analysis and perspectives on the topic at hand.
• Books and book chapters: These sources can provide comprehensive overviews of a particular topic and can also offer theoretical frameworks and historical perspectives.
• Government reports and studies: Government agencies may have conducted studies on the role of filter bubbles in perpetuating political echo chambers.
• News articles and media reports: These sources can provide insight into the current state of the issue, as well as opinions from various stakeholders.
• Online sources: Websites, blogs, and online forums can provide a range of perspectives on the topic and can also be useful in exploring the experiences of individuals who are affected by filter bubbles and political echo chambers.
• Data and statistics: Relevant data and statistics on the prevalence and impact of filter bubbles and political echo chambers in the UK can be useful in providing evidence to support your arguments.
• Expert interviews and focus groups: Conducting expert interviews or focus groups with individuals who have experience with or knowledge of the topic can provide valuable insights and perspectives that can be used to support your arguments.

You can also try using ChatGPT to paraphrase text. ChatGPT can quickly generate a number of different paraphrases of the same idea. You can keep typing “again” in the chat until you are satisfied with the result.

This kind of paraphrasing can be helpful to, for example, non-native speakers who want to improve the fluency of their text. However, be careful. The paraphrases often:

• Contain grammatical errors
• Include false information

So you should always check the output to make sure it’s correct. If you’re unsure, you can run the text through the Scribbr Grammar Checker and cross-reference the information against other, more credible sources .

An alternative is to use the Scribbr Paraphrasing Tool , which was designed directly for this purpose.

Paraphrase the following text:

“A filter bubble results from a social media algorithm’s attempts to cater to an individual user based on data such as their search history and previous behaviour on the site. It results in the user only being presented with information that confirms their biases.”

Restructure the sentences and use other phrasings for the following parts:

• “results from”
• “only being presented with”

“A filter bubble is created when a social media algorithm customises its content for a particular user based on their data, such as their search history and past actions on the platform. This leads to the user being confined to information that reinforces their pre-existing beliefs.” Note We strongly advise against having ChatGPT write text for you and trying to pass it off as your own work. This is academically dishonest and is widely considered plagiarism . It will usually result in an automatic fail, as well as other potential consequences .

You can also use ChatGPT to get feedback on the argumentation and structure of your paper and suggestions for improvements.

An advantage of this is that you can get feedback from ChatGPT on different text excerpts at any time. However, one downside is that ChatGPT does not have a deep understanding of your research question, so its feedback and suggestions may be shallow or inappropriate.

This kind of feedback cannot replace input from an experienced academic supervisor who’s familiar with your topic. Use ChatGPT feedback as a supplement, not a substitute for human feedback.

If you need in-depth feedback on your writing from someone with academic expertise, try Scribbr’s Proofreading & Editing service .

[Text you want to get feedback on.]

Thank you for submitting your research paper for review. Let me provide you with my constructive criticism:

Clarity of Explanations: Overall, the explanations are clear and concise, but there are a few areas that could benefit from additional clarification. For example, in the first paragraph, you mention “the mental lexicon,” but do not provide a definition or further explanation for what this is. It would also be helpful to provide a definition of “lemma.”

Smoothness of Language: The language in the paper is generally smooth, but there are a few instances where it could be refined. For example, the sentence “The symptoms vary from adding superfluous words and taking pauses to hoarseness of the voice” could be rephrased to “The symptoms of these disorders can range from excessive use of words and pauses to hoarseness.”

Structure of Text: The structure of the text is clear, with each paragraph building on the previous one. However, the transition between the first two paragraphs could be smoother. Perhaps you could add a sentence or two to bridge the gap between the two topics.

Even though ChatGPT is a powerful writing tool, you should keep the following limitations in mind:

No original research

Risk of plagiarism, fake sources, fake “facts”.

ChatGPT was trained using existing texts, and the texts created by the AI are based on this data. It’s not capable of doing its own research, only of synthesizing sources that it was trained on.

Additionally, because the texts that it was trained on only go up to 2021, it’s unfamiliar with more recent world events, cultural trends, and developments in different fields of research. This means it may provide outdated information.

Because ChatGPT was trained using existing text, the AI tends to reuse that content in a way that may be considered plagiarism. The AI may copy text from an online publication in its responses.

Additionally, using ChatGPT to write your assignment for you is considered plagiarism regardless of where it got the content from, because you’re passing off something you didn’t write as your own work.

ChatGPT was trained on a wide variety of sources, but it’s not able to accurately tell you what sources it’s using for any given output. Worse, it has a tendency to make up sources that don’t actually exist when you ask.

In addition, ChatGPT is not designed as a citation generator and cannot add correctly formatted citations to your work. Instead, try a tool designed for this purpose, like the Scribbr Citation Generator .

ChatGPT is not always trustworthy when it comes to giving you factually correct information. While it doesn’t deliberately lie, it also doesn’t have “knowledge” in a traditional sense, and it lacks the ability to verify its claims.

Instead, its responses are based on recognising and reproducing patterns that it has seen in other texts. This means that if it doesn’t “know” something, it tends to guess. And its guesses are presented with full confidence, just like established facts.

So it’s very important that you carefully check any factual claims made by ChatGPT against more credible sources —and don’t cite ChatGPT as a source of factual information for your research.

If you want more tips on using AI tools , understanding plagiarism , and citing sources , make sure to check out some of our other articles with explanations, examples, and formats.

• Citing ChatGPT
• Best grammar checker
• Best paraphrasing tool
• ChatGPT in your studies
• Is ChatGPT trustworthy?
• Types of plagiarism
• Self-plagiarism
• Avoiding plagiarism
• Academic integrity
• Best plagiarism checker

Citing sources

• Citation styles
• In-text citation
• Citation examples
• Annotated bibliography

Yes, ChatGPT is able to create code in different programming languages like Python, Java and C++.

There are several ways you can use ChatGPT in your studies , such as if programming is part of your bachelor’s or master’s degree.

You should not trust ChatGPT’s results unconditionally. While you can use ChatGPT during your studies to clarify questions, you should always double-check the answers you receive against other credible sources , as it doesn’t always give correct information. Don’t cite ChatGPT as a source of factual information.

Cite this Scribbr article

If you want to cite this source, you can copy and paste the citation or click the ‘Cite this Scribbr article’ button to automatically add the citation to our free Reference Generator.

Caulfield, J. & Solis, T. (2023, May 15). Using ChatGPT for Assignments | Tips & Examples. Scribbr. Retrieved 27 May 2024, from https://www.scribbr.co.uk/using-ai-tools/using-chatgpt-for-assignments/

Is this article helpful?

Jack Caulfield

Other students also liked, how to use chatgpt in your studies, academic integrity vs academic dishonesty, applying the craap test & evaluating sources, still have questions.

Teaching with ChatGPT: Assignment Design Tips & Ideas

Generative AI offers opportunities for learning, but instructors should guide students on using it safely, ethically, and within the parameters set by course policy. Continue to uphold assignment and assessment design that reinforces good teaching and learning practices. Use AI for teaching where appropriate and when it adds value.

Oregon State University’s “ Bloom’s Taxonomy Revisited ” provides a framework for assignment and assessment design in the age of AI.

Assignment Strategies with Generative AI in mind

• Use authentic assessment, formative assessment, assessment add-ons like problem-solving logs, exam wrappers, minute papers, “muddiest point” questions. Learn more: Assignments & Assessments
• Engage diverse media.  Replace an essay or short-answer writing assignment with one that requires students to submit an audio file, podcast, video, speech, drawing, diagram, or multimedia project. 
• Create connections to real-world experience that AI will not have. Connect assignments to very recent events or new conversations in the field; to issues specific to the local community; or to discussions that took place in your own classroom. Alternatively, ask your students to find a connection between course concepts/topics and their personal experience or knowledge.
• For example: instead of the traditional essay, which may now be easy to cheat through, assign a multimedia project accompanied by a brief self-reflective essay.
• Assign social annotation . For short reading responses, instead of using open-ended questions in Canvas, try social annotation tools that require students to engage with a text along with their classmates. Try Hypothes.is or Perusall , both of which are supported by the University.
• Set clear course AI policies and expectations for assignments.
• Teach your students to cite generative AI correctly.
• Teach your students to use generative AI safely. ChatGPT acknowledges that they may share account holders’ personal information with third parties, including vendors and service providers — see their Privacy Policy . Teach your students to never share personal and sensitive information with generative AI chatbots.
• Model how to use generative AI as a personalized tutor .
• Idea 1: Critical evaluation of AI outputs.  Ask your students to 1. generate a ChatGPT response to a question of their own choosing, related to the field,  2. examine that response, and 3. write a short analytical essay about ChatGPT’s response’s strengths and weaknesses. *In this basic form, this exercise can be a great critical thinking exercise. It can also be tailored to other specific learning goals. For example, if you are looking to teach assessment and evaluative skills, you can ask your students to also come up with a set of assessment criteria, as opposed to the free-form discussion of the strengths and weaknesses.
• Idea 2: Applying concepts to analyze data. Ask your students to: 1. pick a concept related to the field. 2. ask ChatGPT to describe three applications of that concept. 3. rank those applications from most successful to least successful. 4. Explain your thought process behind the rankings. *This can be a written homework assignment or a classroom discussion activity. 
• Idea 3: Identifying and understanding generative AI. Give your students two short human-written pieces or reading responses on a topic related to the field, and one AI-written piece on the same topic. The human-written pieces can be anything — student works, excerpts from publications, or any relevant online materials. Do not tell your students which one of the three pieces is AI-generated. Ask them to examine all three written pieces and 1. identify the AI-generated piece, 2. reflect on their thought-process: how difficult (or how easy) was it for them to identify the AI generated piece? what made them think it is AI-generated? in what ways does it stand out? *This exercise can also can be done as a discussion activity in the classroom or as a written assignment. Whichever format you choose, make sure that the essays are short enough and manageable to read in that specific format.
• OFE collection of sample assignments using AI (Google Doc, requires a Montclair account). If you have an assignment that uses AI to help student learning, we invite you to share it with colleagues at Montclair. To have your assignment added to our collection, request editing access to this Google doc, or simply email a copy of that assignment to Vera at [email protected].
• University of North Dakota’s AI Assignment Library of peer-reviewed assignment ideas
• For example: Instead of one large submission due on May 5th, try assigning a project outline due April 1st, notes on research articles due Apr 15, first draft due Apr 25, and final draft due May 5th.
• Review your grading criteria and rubrics to make sure you’re setting your students up to adopt strong learning strategies. See Grading for Learning under Plan for Grading .
• For example: Have students write responses in class. If students have 20 minutes to write brief responses to the kinds of questions you might have provided as homework, they will learn a great deal, and as a bonus, your subsequent class discussion will benefit from that engaged individual work.
• Have students respond orally, requiring each student to respond to a different question.
• Have students work in small groups in class to present on topics in class.
• Incorporate brief in-class quizzes, tests and other assessments. The key is to make these short, frequent, and possibly even unannounced. They serve assessment purposes, reward attendance, and provide useful immediate feedback about learning. Small point values for individual assessments allow poor performance to be informative to students rather than disastrous.
• Engage visuals: ask students to respond to images or videos in their assignment. Be sure to include alt-text for accessibility.
• For example: “Refer to two of the theorists discussed in class.”
• Try requiring handwritten responses where scope permits. Students will groan, and you may too as you attempt to read student handwriting again, but not only will this deter the use of ChatGPT, but some research shows that we actually remember better when we write by hand. Varying the way we engage with thinking has value as it plays to different students’ preferences, and stretches all of us to try new ways to help us focus on the task of thinking.
• Employ Simple Active Learning Strategies : In-class and in homework, active learning assignments inspire learning.
• Collaborative Learning : Sometimes called team or group learning, collaborative learning can be designed to accelerate learning.

Montclair’s Digital Accessibility Initiative , ITDS , and DRC offer a variety of resources for faculty to create accessible materials for students. Following Universal Design for Learning principles benefits all students.

Generative AI tools that enhance functions such as text to speech, speech to text, text to image, voiceovers, image descriptions, and PDF paraphrasing can potentially increase the accessibility of assignments and classroom materials for students with disabilities.

• McDermott, B. (2024). AI as an Accessibility Tool: Using Generative AI to Support Universal Design for Learning Approach. In S. Mahmud (Ed.), Academic Integrity in the Age of Artificial Intelligence (pp. 162-174). IGI Global. https://doi.org/10.4018/979-8-3693-0240-8.ch009
• TriCollege Libraries (Bryn Mawr, Haverford, Swarthmore)’s “ Generative AI in Higher Education ”. Page has sub-sections on AI assistive technologies and accessibility.
• University of Cincinnati Libraries’ “ AI Tools for Accessibility “

Last Modified: Tuesday, April 9, 2024 5:36 pm

Outsmart ChatGPT: 8 Tips for Creating Assignments It Can’t Do

• Share article

Since the latest version of ChatGPT emerged late last year, educators have been puzzling over how to reconcile traditional writing instruction with tech that can churn out everything from essays to haikus with uncanny sophistication.

Some educators contend ChatGPT can be a learning tool, while others say it’s more likely to be used as a cheating tool. In fact, more than a quarter of teachers say they’ve caught students using ChatGPT to cheat, according to a survey from Study.com, an online learning platform .

That raises the question: Can educators remove students’ temptation to use ChatGPT and other so-called “large language models” to plagiarize by coming up with assignments that the ChatGPT won’t be able to handle? If yes, what might those assignments look like?

We asked educators and experts on all sides of the broader debates about ChatGPT to give us some strategies for AI-proofing assignments. Here’s what they told us:

1. Ask students to write about something deeply personal

Consider having students delve into their scariest moment, the biggest challenge they ever overcame, or even answer a quirky personal question: Would you rather be the bucket or the sand?

It’s difficult at this point for AI to fake highly personal writing, said Joshua Rosenberg, an assistant professor of STEM education at the University of Tennessee in Knoxville. (For the record, Rosenberg thinks it’s valuable for teachers to incorporate AI writing tools into some assignments.)

To be sure, even with these personal essays, students “could make it up,” acknowledged Kristin Daley Conti, a 7th grade science teacher at Tantasqua Junior High School in Massachusetts. But most of her middle schoolers are too eager to share their stories to outsource the job to AI, she explained. “They like to center things around themselves,” she said.

One wrinkle: Writing only about personal heroes or big life challenges isn’t as effective as other types of assignments for teaching students the reasoning and critical thinking skills that good writers must master, said Michelle Brown, the founder and CEO of CommonLit, an online reading program.

“I cringe a little bit at the idea that we will overcorrect and make a lot of writing personal,” she said. “What makes writing instruction good is that you’re synthesizing complex information from a complex text or complex sources. So, if we’re trying to make our assignments ChatGPT-proof that could be one way, but I worry about the consequences on student learning.”

2. Center a writing assignment around an issue specific to the local community

ChatGPT doesn’t have a strong background in hyperlocal issues, though that is likely to change as the tool becomes more sophisticated, experts say. But for now, educators may be able to minimize how much help ChatGPT can be on a particular assignment by grounding it in the school community—maybe even by asking students to write about a new school rule or the student council election.

Teachers could also ask their students to connect information about the water quality in a nearby pond the class studied to global patterns in environmental conservation. “There probably just isn’t a lot of data” available online about such a small body of water, Rosenberg said.

Did We Miss Anything?

Got a tip for making assignments ChatGPT-proof not mentioned here?

📧 Email [email protected] with your ideas.

3. Direct students to write about a very recent news event

At this point, ChatGPT can’t capture much information about things that happened just days earlier, Rosenberg said. Teachers could ask students to compare a very recent news event to a historical one, say the balloon that was reportedly sent by the Chinese government to spy on the United States with the Cuban missile crisis.

While ChatGPT may be able to spit out some sort of answer, it is likely to be muddled, Rosenberg said. “The model might generate just factually wrong things about time-sensitive events,” he said. “That can be a good cue to teachers that something’s fishy.”

4. Have students show or explain their work

In math class, students usually show how they arrived at a particular answer to get credit for solving a problem. That concept could apply to writing, Rosenberg said. For instance, teachers could prompt students to detail their brainstorming process, explaining why they choose to write about a particular topic.

Teachers could also ask questions such as: “How did you decide to structure your paper this way? Did you just start writing or did you think ‘my first paragraph is going to be on this and then my second paragraph on this?’” Rosenberg said. “That could just hold students a little bit more accountable for their process of writing.”

On a similar note, two literacy focused technology nonprofits, CommonLit and Quill, would love to see developers come up with new technology that analyzes keystrokes or various versions of a draft to decide whether a particular piece of writing was produced by a human or a robot, a more sophisticated process-based approach to discouraging cheating.

5. Ask students to give an oral presentation, along with the written work

One way to make this work: Ask students to record themselves on a video platform such as FlipGrid, talking about their essay, story, report, or other assignment, Daley Conti, the middle school science teacher, suggested.

That could deter cheaters. And it would provide students who did get help from AI in completing their assignment with an incentive to at least learn the content. “Even if they did get it from ChatGPT, they would have had to read it, digest it, and then talk about it,” Daley Conti said.

6. Return to a pre-digital age and ask students to handwrite their essays in class

This low-tech solution seems obvious. And it might be the most surefire way to make certain that students aren’t getting help from AI or even their parents or other students in the class.

Sal Khan, founder of one of the most prominent education technology tools, Khan Academy, sees value in having students do their writing the old-fashioned way , even as he thinks K-12 schools should help students learn to write using ChatGPT as well.

“One mitigation, which isn’t a bad idea, is to have students do more writing in class periods, in front of you,” Khan said in an interview. “I think it’s a good idea to do more of your actual writing and workshopping in class. The best writing classes are the ones where it’s like a real writers’ workshop, and kids are writing all the time. And the teacher and peers are giving each other feedback.”

7. Put project-based learning to work

Teachers could lean towards big, multi-disciplinary projects that an AI essay “isn’t going to be an appropriate measure of,” said Joseph South, the chief learning officer for the International Society for Technology in Education, a nonprofit.

For instance, he said, several school districts explored water quality in different parts of the country for a social studies course, looking at different policies in different states and cities. They tested the water in their own communities, looking for contaminates. Then they created graphs and charts showing the impact of local policies on local water supplies, and presented their findings.

“ChatGPT was never going to do that project for them,” South said. “It’d be impossible to cheat on that project with it. And the kids didn’t want to cheat because they were doing something really cool and interesting and relevant to their lives.”

If students are “taking pride in their work, they don’t want a robot to write it,” he said.

8. Run the assignment through ChatGPT before giving it to students

Maybe asking students for their take on a local issue—the school board election, perhaps—is one way to get around the power of ChatGPT. One hiccup: If users point ChatGPT to specific sources, it will use them in crafting a response to a prompt. So, if students put in links to a few articles in the local newspaper about the election, the tech may produce a surprisingly sophisticated take.

Teachers hoping to come up with assignments the tool can’t handle should keep that in mind, said Peter Gault, the founder and executive director of Quill, a literacy-focused technology nonprofit. “The trick is if you could say read this article, and then give a link and then do it and then see how it performs,” he said.

Sign Up for EdWeek Tech Leader

Edweek top school jobs.

Sign Up & Sign In

Faculty Help: Generative AI Resource Guide: Writing Assignments

• ChatGPT 101
• Discussion in the Higher-Ed Community

Writing Assignments

• AI in the Classroom
• Plagiarism & Academic Integrity
• AI Detectors
• Sample Syllabus Policies
• Faculty Uses for AI
• SFCC Library and ChatGPT
• Other Text Generators
• Ethical Considerations
• Articles, Videos and Open Web Content
• Guidance, Tips & Ideas
• Writing Assignments You Can (Probably) Use Right Now

How are educators approaching the redesign of writing assignments? Each of these links is customized to take you to highly focused and relevant content exclusively from that website or domain.

And we invite you to explore this website: MLA-CCCC Joint Task Force on Writing and AI  "The MLA and CCCC have formed a joint task force to develop resources, guidelines, and professional standards around the use of AI and writing."

• Inside Higher Ed
• Chronicle of Higher Education
• Faculty Focus
• Times Higher Education
• Colleges and Universities Content from other colleges and universities about redesigning and rethinking writing assignments
• Google Scholar
• arXiv - Cornell University arXiv is a free distribution service and an open-access archive for 2,266,443 scholarly articles in the fields of physics, mathematics, computer science, quantitative biology, quantitative finance, statistics, electrical engineering and systems science, and economics. Materials on this site are not peer-reviewed by arXiv.

Click here to see what the SFCC Library databases have on the topic of ChatGPT and student writing.

Learn more about designing writing-based assignments, activities, and assessments in the age of AI at this writing workshop led by Dr. Maddie Holland.

AI has already been used to help students with things like grammar and plagiarism detection, but what about the actual college essay-writing process? Will a computer write a well-written and thoughtful essay? Or will it just spit out something generic and unoriginal? How will the colleges address the issue of AI in essays? Cyndy has invited Brad Schiller, from Prompt, to discuss how AI may change the admissions landscape. Watch Brad demonstrate the power and the limitations of ChatGPT in writing essays.

ChatGPT and other artificial intelligence (AI) language models have the potential to transform education. How can we balance the potential for innovation and the challenges to academic integrity in the teaching of writing across the disciplines? Join us to discuss the significance of AI in academic writing and strategies for embracing, detecting, or preventing students’ use of AI-generated text. Stephen (Chip) Gladson (Professor of English and College-wide Coordinator of Writing in the Disciplines, Montgomery College) Moderator: Michael Mills (Vice President, Office of E-Learning, Innovation and Teaching Excellence, Montgomery College)

This workshop was recorded April 13, 2023 and is intended for health sciences faculty who provide curricular writing assignments.

This is a more focused list of resources aimed specifically at guidance, tips and ideas for redesigning writing assignments in the age of AI.

• Understanding 'wraiting' (writing with AI) | CSU Sacramento
• AI in First Year Writing Courses | Marc Watkins
• Sample Assignments: Writing and Technology | UMass Amherst Writing Program
• Guide, Don’t Hide: Maximizing Course Assignments with ChatGPT Integration | Faculty Focus
• Writing responsibly: how to use reflective practices to navigate ChatGPT | Times Higher Education
• Instructors Rush to Do ‘Assignment Makeovers’ to Respond to ChatGPT | EdSurge
• Teaching Writing with Generative AI | Leon Furze
• Assigning AI: Seven Ways of Using AI in Class | One Useful Thing
• 3 ways to use ChatGPT to help students learn – and not cheat | The Conversation
• Designing Assignments Effectively | Georgetown University
• Understanding AI Writing Tools and their Uses for Teaching and Learning at UC Berkeley | Center for Teaching & Learning Scroll down to Suggested Writing Prompts and Activities
• How can I incorporate ChatGPT into the writing process? | CTLO
• Teaching with ChatGPT: Assignment Design Tips & Ideas | Montclair State University
• AI Guidance | Yale University Poorvu Center
• From AI to A+: Prepare Your Students for Using ChatGPT and other AI | Medium, Ryan Watkins
• Teaching with Generative AI | U. of Pittsburg
• Course Design - ChatGPT and other AI-based tools | U. of Washington

Many of these you'll probably be able to use and even change as you see fit. However, please sure check for a Creative Commons license; if none is listed please reach out to the creator. If nothing else, they will hopefully give you some ideas. 🧠 

• AI Pedagogy Project "An evolving collection of curated assignments that integrate AI tools from educators around the world."
• Generative AI Activities for the Writing & Language Classroom | Anna Mills Microlesson on critical AI literacy we can use to give context when we incorporate AI; classroom uses of text generation that also promote critical scrutiny of AI
• Artificial Intelligence Tools Scroll dwown to Category 3 for AMAZING assignment ideas!
• AI in the Classroom | Butler University
• "What Kind of Writer am I?” Autoethnography Essay © 2023 by Laura Dumin is licensed under CC BY-NC 4.0 Original Link: https://ucok-my.sharepoint.com/:w:/g/personal/ldumin_uco_edu/ER3uWZRtRQtPkIgab85AFUEBY8FO0S7kw4roh8SrvnDc6A?rtime=xCYyZN9X20g
• ChatGPT Exercise | Mike Ryan, Texas Tech University
• Professional Letter Assignment | Suzanne Tapp, Texas Tech University
• Discussion Board Assignment Task: Using ChatGPT, write two paragraphs of text on your research topic; analyze and evaluate the ChatGPT information; and report your findings to the class. Purpose: Find productive directions for your essay, evaluate AI-generated content as it relates to your topic, and get feedback from the class. Created by Lyn Megow (Eastern Washington University, Spokane Falls Community College) CC License: BY NC
• Humanities Example_ English_Ryan Wepler_Yale
• Assigning AI: Seven Approaches for Students, with Prompts | SSRN The authors propose seven approaches for utilizing AI in classrooms: AI-tutor, AI-coach, AI-mentor, AI-teammate, AI-tool, AI-simulator, and AI-student, each with distinct pedagogical benefits and risks.
• Incorporating AI in Teaching: Practical Examples for Busy Instructors Since January 2023, I’ve talked with hundreds of instructors at dozens of institutions about how they might incorporate AI into their teaching.
• Alternative Strategies for Artificial Intelligence in the Writing Classroom | Teachers & Writers Magazine
• Assignment Considerations & Ideas | Butler University Library

Copy and paste this search into Google for highly-focused, relevant results! site:edu ("generative AI" OR chatgpt) assignments (advice OR best practices OR guidance)  

• << Previous: Discussion in the Higher-Ed Community
• Next: Assessment >>
• Last Updated: May 28, 2024 3:51 PM
• URL: https://libraryhelp.sfcc.edu/Chat-GPT

Teaching With A.I.

CNDLS is here to support you as you navigate the uses of generative AI in your teaching and research. We’re developing an evolving set of resources on this site to help you understand the current state of Artificial Intelligence in higher education, including assignment design, policies for your course, and more.

Assignment Design

Review or (re)design assignments to ensure you’re achieving your learning goals.

Course Policies

Be transparent with students about expectations surrounding AI tools, and whether or not they can be used in your class.

Events & Opportunities

Attend a wide range of workshops designed to support many experience levels, and check out other opportunities.

Explore types of AI tools, understand how students are using them, and connect with us for help as you need it.

Related Topics

Read some of the key topics affiliated with using AI, including bias and data.

Latest on AI from CNDLS

This spring, we’re running a wide range of virtual workshops to help you think about the role AI plays in your teaching. See the Events and Opportunities section to view the schedule.

• Please reach out to CNDLS you have any questions about the use of generative AI tools like ChatGPT in the classroom, or want to request a workshop for your academic unit.
• Contact the Writing Program to discuss ways of thinking about the role of writing, teaching writing, and any other related issues.
• Refer to the Academic Honor Council ’s guidance in the Standards of Conduct regarding the use of AI tools in individual courses.

Points of Entry

• How are students using AI tools?
• How can I redesign my assignments and exams to maintain my learning goals for my students?
• What’s the University’s policy on students using AI in the classroom?
• How would I know if one of my policies has been violated (i.e. that student has used AI)?
• What do I do if I think a policy has been violated?
• Whom can I talk to about AI-related policies?
• Where can I learn more about data privacy?

Artificial intelligence in assignment writing

Many students are uncertain about the rules for using aids and collaboration when writing assignments, and with the emergence of new tools based on artificial intelligence, such as ChatGPT, there may be more questions than before. It is therefore important that you as a student know and understand the rules.

Please note that there may be  different guidelines  in different subjects. If you are unsure about what applies to your subject, you can contact the person responsible for the course .

Artificial Intelligence (AI) can be a useful tool in assignment writing, but you must follow the academic and ethical guidelines for academic writing. When using AI, you should be aware of how you use it and what kind of contribution it makes to your text.

It is important to know the rules for citation and how to cite the sources you have used, including AI, both in the text itself and in a reference list. You must also know what is considered cheating and plagiarism to avoid serious mistakes, whether intentional or unintentional.

When writing an academic paper, you must always refer to the sources you have used. This also applies when using artificial intelligence. Learn more about the rules for citations in the  Citation Compass . Here you will find instructions on how to reference the use of artificial intelligence .  

The University Library offers  courses in source criticism and reference management .

For each exam, information about citations and the bibliography is provided. You can get information from the person responsible for your course. Additionally, it will be displayed on the front page of the test in Inspera for home exams.

As a general rule, all aids are allowed in home exams and assignment submissions. Language models like ChatGPT are considered legal aids in exams where all aids are permitted. However, if you submit text, calculations, or similar that are directly copied from a language model without referring to the aid you have used, it is considered cheating since you are presenting someone else's work as your own. 

Cheating and plagiarism

Plagiarism and cheating in exams are serious offenses that can have consequences for your right to study and your grades.

• Plagiarism is using someone else's texts, ideas, images, or other material without citing the source or giving acknowledgment
• Cheating is using illegal aids, collaborating with others, or cheating in other ways during exams 

If a student is suspected or caught for plagiarism or cheating, the case will be handled in the university's appeals committee. The consequence can be various reactions, such as annulment of the exam or exclusion from the university for up to two semesters. You can read more about plagiarism and cheating on this page .

Examples of the use of artificial intelligence

Can i use ai for ideas or structure in my assignment.

You can use a language model to generate ideas or arguments, but you need to be cautious and critical when doing so. A language model can help you develop or expand your topic or issue by giving you suggestions based on your text or a keyword. A language model can also assist you in finding or formulating supporting or opposing arguments by providing examples, sources, or counterarguments.

How to reference correctly?

If you have used AI as a tool to write an academic paper, you should refer to it in the text and in the reference list in your chosen referencing style. A reference to AI should include the name of the language model, the developer or provider of the language model, the version or date of the language model, and the URL or platform where you used the language model. In the text or in a footnote, you can also explain how you have used the language model and what kind of contribution it has made to the text.

A reference to GPT UiO based on APA7 style could look like this:

In this paper, I have used the language model GPT-3 (OpenAI, 2020) through GPT UiO (University of Oslo, 2021) to generate ideas and arguments for my text. GPT UiO is a UiO-developed service that allows me to use OpenAI's GPT models within privacy requirements. I have used GPT UiO to suggest topics, issues, hypotheses, and research questions for the assignment, and to find or formulate supporting or opposing arguments for these. I have not used GPT UiO to write entire paragraphs or chapters, but only to make suggestions that I have evaluated and processed myself.

In the reference list, the reference to GPT UiO will look like this:

OpenAI. (2020). UiO GPT (Version GPT-3.5 Turbo) [Large language model]. University of Oslo.

Learn more about references in the  Citation Compass . 

Can I use AI for proofreading?

AI can assist you with language correction in your assignment, but you must be aware that AI cannot replace a thorough manual proofreading or expert guidance from your instructor. Additionally, using AI for language correction may not be appropriate for language-related subjects, and different academic communities may have varying guidelines regarding its use. If you are uncertain about the guidelines specific to your subject, you can reach out to your course instructor.

As a student, it's essential to exercise caution when using AI in your assignments. Please take note of the following:

• You are expected to submit a text that is solely produced by you. Submitting a text that is fully or partially produced by AI or someone else without appropriate declaration is considered cheating. 
• Language models generate text based on probability and common phrases, which may lack your unique and academic expression.
• You should also be careful to avoid sharing sensitive data or personal information.

You can be specific in your request to the tool. For example, you can ask for help with finding grammatical errors, improving sentence structure, or requesting synonyms to avoid repetition. Remember that all suggestions should be evaluated and possibly adapted to the context of your assignment.

By using ChatGPT or similar AI tools in a responsible and critical manner, you can improve the language quality of your exam assignment. Remember that AI can be used as a tool, but the final text and responsibility for the content rests with you as a student.

How to reference correctly? 

A reference to GPT UiO based on the APA7 style could look like this in the text or in a footnote:

In the process of preparing this assignment, 'UiO Chat,' an AI-based tool for proofreading and linguistic improvement, was used to identify and correct grammatical errors and to improve sentence structure. This assistance was crucial for ensuring linguistic clarity and correctness in the text (UiO Chat, 2023).

In the reference list, the reference to GPT UiO would look like this:

See more in the  Citation Compass .

Is it allowed to copy AI-generated text into my assignment?

Copying text from AI into your assignment without acknowledging it, is considered plagiarism, and it can have significant consequences. Therefore, you should always exercise caution when using artificial intelligence in your assignments.

Please be aware of the following:

• As a student, it is expected that you submit independently produced text. Submitting a text that is fully or partially generated by AI or others without proper acknowledgement is considered plagiarism.
• Language models generate text based on probability and commonly used phrases, which may result in text lacking your own academic and independent touch.
• It is also important to be mindful and avoid sharing sensitive data or personal information when utilising AI. 

Even though you might insert a paragraph referencing the language model, it may not be advisable. It is difficult to precisely define when a text ceases to be an independent product. For example, if you include a paragraph to illustrate how AI can be used, you must clearly indicate in the text or a footnote which paragraph(s) were generated by AI and disclose the input you provided to the AI beforehand.

Remember that you are responsible for the content of your assignment, so it is essential to be meticulous in checking the content and references. There are examples of cases where language models have provided wrong facts or pointed to non-existent sources. 

How to reference correctly 

If you insert a text paragraph, you must mark it in a clear and correct manner, either in the text or a footnote. For example, This paragraph was generated with the help of [Name of AI tool], based on input: '[your specific request to the AI tool]'.

In your reference list, the reference to GPT UiO would look like this:

See more in the Citation Compass . 

• Share on Facebook
• Share on Twitter

A systematic literature review of empirical research on ChatGPT in education

• Open access
• Published: 26 May 2024
• Volume 3 , article number  60 , ( 2024 )

Cite this article

You have full access to this open access article

• Yazid Albadarin   ORCID: orcid.org/0009-0005-8068-8902 1 ,
• Mohammed Saqr 1 ,
• Nicolas Pope 1 &
• Markku Tukiainen 1  

Over the last four decades, studies have investigated the incorporation of Artificial Intelligence (AI) into education. A recent prominent AI-powered technology that has impacted the education sector is ChatGPT. This article provides a systematic review of 14 empirical studies incorporating ChatGPT into various educational settings, published in 2022 and before the 10th of April 2023—the date of conducting the search process. It carefully followed the essential steps outlined in the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA 2020) guidelines, as well as Okoli’s (Okoli in Commun Assoc Inf Syst, 2015) steps for conducting a rigorous and transparent systematic review. In this review, we aimed to explore how students and teachers have utilized ChatGPT in various educational settings, as well as the primary findings of those studies. By employing Creswell’s (Creswell in Educational research: planning, conducting, and evaluating quantitative and qualitative research [Ebook], Pearson Education, London, 2015) coding techniques for data extraction and interpretation, we sought to gain insight into their initial attempts at ChatGPT incorporation into education. This approach also enabled us to extract insights and considerations that can facilitate its effective and responsible use in future educational contexts. The results of this review show that learners have utilized ChatGPT as a virtual intelligent assistant, where it offered instant feedback, on-demand answers, and explanations of complex topics. Additionally, learners have used it to enhance their writing and language skills by generating ideas, composing essays, summarizing, translating, paraphrasing texts, or checking grammar. Moreover, learners turned to it as an aiding tool to facilitate their directed and personalized learning by assisting in understanding concepts and homework, providing structured learning plans, and clarifying assignments and tasks. However, the results of specific studies (n = 3, 21.4%) show that overuse of ChatGPT may negatively impact innovative capacities and collaborative learning competencies among learners. Educators, on the other hand, have utilized ChatGPT to create lesson plans, generate quizzes, and provide additional resources, which helped them enhance their productivity and efficiency and promote different teaching methodologies. Despite these benefits, the majority of the reviewed studies recommend the importance of conducting structured training, support, and clear guidelines for both learners and educators to mitigate the drawbacks. This includes developing critical evaluation skills to assess the accuracy and relevance of information provided by ChatGPT, as well as strategies for integrating human interaction and collaboration into learning activities that involve AI tools. Furthermore, they also recommend ongoing research and proactive dialogue with policymakers, stakeholders, and educational practitioners to refine and enhance the use of AI in learning environments. This review could serve as an insightful resource for practitioners who seek to integrate ChatGPT into education and stimulate further research in the field.

Similar content being viewed by others

Empowering learners with ChatGPT: insights from a systematic literature exploration

Incorporating AI in foreign language education: An investigation into ChatGPT’s effect on foreign language learners

Large language models in education: A focus on the complementary relationship between human teachers and ChatGPT

Avoid common mistakes on your manuscript.

1 Introduction

Educational technology, a rapidly evolving field, plays a crucial role in reshaping the landscape of teaching and learning [ 82 ]. One of the most transformative technological innovations of our era that has influenced the field of education is Artificial Intelligence (AI) [ 50 ]. Over the last four decades, AI in education (AIEd) has gained remarkable attention for its potential to make significant advancements in learning, instructional methods, and administrative tasks within educational settings [ 11 ]. In particular, a large language model (LLM), a type of AI algorithm that applies artificial neural networks (ANNs) and uses massively large data sets to understand, summarize, generate, and predict new content that is almost difficult to differentiate from human creations [ 79 ], has opened up novel possibilities for enhancing various aspects of education, from content creation to personalized instruction [ 35 ]. Chatbots that leverage the capabilities of LLMs to understand and generate human-like responses have also presented the capacity to enhance student learning and educational outcomes by engaging students, offering timely support, and fostering interactive learning experiences [ 46 ].

The ongoing and remarkable technological advancements in chatbots have made their use more convenient, increasingly natural and effortless, and have expanded their potential for deployment across various domains [ 70 ]. One prominent example of chatbot applications is the Chat Generative Pre-Trained Transformer, known as ChatGPT, which was introduced by OpenAI, a leading AI research lab, on November 30th, 2022. ChatGPT employs a variety of deep learning techniques to generate human-like text, with a particular focus on recurrent neural networks (RNNs). Long short-term memory (LSTM) allows it to grasp the context of the text being processed and retain information from previous inputs. Also, the transformer architecture, a neural network architecture based on the self-attention mechanism, allows it to analyze specific parts of the input, thereby enabling it to produce more natural-sounding and coherent output. Additionally, the unsupervised generative pre-training and the fine-tuning methods allow ChatGPT to generate more relevant and accurate text for specific tasks [ 31 , 62 ]. Furthermore, reinforcement learning from human feedback (RLHF), a machine learning approach that combines reinforcement learning techniques with human-provided feedback, has helped improve ChatGPT’s model by accelerating the learning process and making it significantly more efficient.

This cutting-edge natural language processing (NLP) tool is widely recognized as one of today's most advanced LLMs-based chatbots [ 70 ], allowing users to ask questions and receive detailed, coherent, systematic, personalized, convincing, and informative human-like responses [ 55 ], even within complex and ambiguous contexts [ 63 , 77 ]. ChatGPT is considered the fastest-growing technology in history: in just three months following its public launch, it amassed an estimated 120 million monthly active users [ 16 ] with an estimated 13 million daily queries [ 49 ], surpassing all other applications [ 64 ]. This remarkable growth can be attributed to the unique features and user-friendly interface that ChatGPT offers. Its intuitive design allows users to interact seamlessly with the technology, making it accessible to a diverse range of individuals, regardless of their technical expertise [ 78 ]. Additionally, its exceptional performance results from a combination of advanced algorithms, continuous enhancements, and extensive training on a diverse dataset that includes various text sources such as books, articles, websites, and online forums [ 63 ], have contributed to a more engaging and satisfying user experience [ 62 ]. These factors collectively explain its remarkable global growth and set it apart from predecessors like Bard, Bing Chat, ERNIE, and others.

In this context, several studies have explored the technological advancements of chatbots. One noteworthy recent research effort, conducted by Schöbel et al. [ 70 ], stands out for its comprehensive analysis of more than 5,000 studies on communication agents. This study offered a comprehensive overview of the historical progression and future prospects of communication agents, including ChatGPT. Moreover, other studies have focused on making comparisons, particularly between ChatGPT and alternative chatbots like Bard, Bing Chat, ERNIE, LaMDA, BlenderBot, and various others. For example, O’Leary [ 53 ] compared two chatbots, LaMDA and BlenderBot, with ChatGPT and revealed that ChatGPT outperformed both. This superiority arises from ChatGPT’s capacity to handle a wider range of questions and generate slightly varied perspectives within specific contexts. Similarly, ChatGPT exhibited an impressive ability to formulate interpretable responses that were easily understood when compared with Google's feature snippet [ 34 ]. Additionally, ChatGPT was compared to other LLMs-based chatbots, including Bard and BERT, as well as ERNIE. The findings indicated that ChatGPT exhibited strong performance in the given tasks, often outperforming the other models [ 59 ].

Furthermore, in the education context, a comprehensive study systematically compared a range of the most promising chatbots, including Bard, Bing Chat, ChatGPT, and Ernie across a multidisciplinary test that required higher-order thinking. The study revealed that ChatGPT achieved the highest score, surpassing Bing Chat and Bard [ 64 ]. Similarly, a comparative analysis was conducted to compare ChatGPT with Bard in answering a set of 30 mathematical questions and logic problems, grouped into two question sets. Set (A) is unavailable online, while Set (B) is available online. The results revealed ChatGPT's superiority in Set (A) over Bard. Nevertheless, Bard's advantage emerged in Set (B) due to its capacity to access the internet directly and retrieve answers, a capability that ChatGPT does not possess [ 57 ]. However, through these varied assessments, ChatGPT consistently highlights its exceptional prowess compared to various alternatives in the ever-evolving chatbot technology.

The widespread adoption of chatbots, especially ChatGPT, by millions of students and educators, has sparked extensive discussions regarding its incorporation into the education sector [ 64 ]. Accordingly, many scholars have contributed to the discourse, expressing both optimism and pessimism regarding the incorporation of ChatGPT into education. For example, ChatGPT has been highlighted for its capabilities in enriching the learning and teaching experience through its ability to support different learning approaches, including adaptive learning, personalized learning, and self-directed learning [ 58 , 60 , 91 ]), deliver summative and formative feedback to students and provide real-time responses to questions, increase the accessibility of information [ 22 , 40 , 43 ], foster students’ performance, engagement and motivation [ 14 , 44 , 58 ], and enhance teaching practices [ 17 , 18 , 64 , 74 ].

On the other hand, concerns have been also raised regarding its potential negative effects on learning and teaching. These include the dissemination of false information and references [ 12 , 23 , 61 , 85 ], biased reinforcement [ 47 , 50 ], compromised academic integrity [ 18 , 40 , 66 , 74 ], and the potential decline in students' skills [ 43 , 61 , 64 , 74 ]. As a result, ChatGPT has been banned in multiple countries, including Russia, China, Venezuela, Belarus, and Iran, as well as in various educational institutions in India, Italy, Western Australia, France, and the United States [ 52 , 90 ].

Clearly, the advent of chatbots, especially ChatGPT, has provoked significant controversy due to their potential impact on learning and teaching. This indicates the necessity for further exploration to gain a deeper understanding of this technology and carefully evaluate its potential benefits, limitations, challenges, and threats to education [ 79 ]. Therefore, conducting a systematic literature review will provide valuable insights into the potential prospects and obstacles linked to its incorporation into education. This systematic literature review will primarily focus on ChatGPT, driven by the aforementioned key factors outlined above.

However, the existing literature lacks a systematic literature review of empirical studies. Thus, this systematic literature review aims to address this gap by synthesizing the existing empirical studies conducted on chatbots, particularly ChatGPT, in the field of education, highlighting how ChatGPT has been utilized in educational settings, and identifying any existing gaps. This review may be particularly useful for researchers in the field and educators who are contemplating the integration of ChatGPT or any chatbot into education. The following research questions will guide this study:

What are students' and teachers' initial attempts at utilizing ChatGPT in education?

What are the main findings derived from empirical studies that have incorporated ChatGPT into learning and teaching?

2 Methodology

To conduct this study, the authors followed the essential steps of the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA 2020) and Okoli’s [ 54 ] steps for conducting a systematic review. These included identifying the study’s purpose, drafting a protocol, applying a practical screening process, searching the literature, extracting relevant data, evaluating the quality of the included studies, synthesizing the studies, and ultimately writing the review. The subsequent section provides an extensive explanation of how these steps were carried out in this study.

2.1 Identify the purpose

Given the widespread adoption of ChatGPT by students and teachers for various educational purposes, often without a thorough understanding of responsible and effective use or a clear recognition of its potential impact on learning and teaching, the authors recognized the need for further exploration of ChatGPT's impact on education in this early stage. Therefore, they have chosen to conduct a systematic literature review of existing empirical studies that incorporate ChatGPT into educational settings. Despite the limited number of empirical studies due to the novelty of the topic, their goal is to gain a deeper understanding of this technology and proactively evaluate its potential benefits, limitations, challenges, and threats to education. This effort could help to understand initial reactions and attempts at incorporating ChatGPT into education and bring out insights and considerations that can inform the future development of education.

2.2 Draft the protocol

The next step is formulating the protocol. This protocol serves to outline the study process in a rigorous and transparent manner, mitigating researcher bias in study selection and data extraction [ 88 ]. The protocol will include the following steps: generating the research question, predefining a literature search strategy, identifying search locations, establishing selection criteria, assessing the studies, developing a data extraction strategy, and creating a timeline.

2.3 Apply practical screen

The screening step aims to accurately filter the articles resulting from the searching step and select the empirical studies that have incorporated ChatGPT into educational contexts, which will guide us in answering the research questions and achieving the objectives of this study. To ensure the rigorous execution of this step, our inclusion and exclusion criteria were determined based on the authors' experience and informed by previous successful systematic reviews [ 21 ]. Table 1 summarizes the inclusion and exclusion criteria for study selection.

2.4 Literature search

We conducted a thorough literature search to identify articles that explored, examined, and addressed the use of ChatGPT in Educational contexts. We utilized two research databases: Dimensions.ai, which provides access to a large number of research publications, and lens.org, which offers access to over 300 million articles, patents, and other research outputs from diverse sources. Additionally, we included three databases, Scopus, Web of Knowledge, and ERIC, which contain relevant research on the topic that addresses our research questions. To browse and identify relevant articles, we used the following search formula: ("ChatGPT" AND "Education"), which included the Boolean operator "AND" to get more specific results. The subject area in the Scopus and ERIC databases were narrowed to "ChatGPT" and "Education" keywords, and in the WoS database was limited to the "Education" category. The search was conducted between the 3rd and 10th of April 2023, which resulted in 276 articles from all selected databases (111 articles from Dimensions.ai, 65 from Scopus, 28 from Web of Science, 14 from ERIC, and 58 from Lens.org). These articles were imported into the Rayyan web-based system for analysis. The duplicates were identified automatically by the system. Subsequently, the first author manually reviewed the duplicated articles ensured that they had the same content, and then removed them, leaving us with 135 unique articles. Afterward, the titles, abstracts, and keywords of the first 40 manuscripts were scanned and reviewed by the first author and were discussed with the second and third authors to resolve any disagreements. Subsequently, the first author proceeded with the filtering process for all articles and carefully applied the inclusion and exclusion criteria as presented in Table  1 . Articles that met any one of the exclusion criteria were eliminated, resulting in 26 articles. Afterward, the authors met to carefully scan and discuss them. The authors agreed to eliminate any empirical studies solely focused on checking ChatGPT capabilities, as these studies do not guide us in addressing the research questions and achieving the study's objectives. This resulted in 14 articles eligible for analysis.

2.5 Quality appraisal

The examination and evaluation of the quality of the extracted articles is a vital step [ 9 ]. Therefore, the extracted articles were carefully evaluated for quality using Fink’s [ 24 ] standards, which emphasize the necessity for detailed descriptions of methodology, results, conclusions, strengths, and limitations. The process began with a thorough assessment of each study's design, data collection, and analysis methods to ensure their appropriateness and comprehensive execution. The clarity, consistency, and logical progression from data to results and conclusions were also critically examined. Potential biases and recognized limitations within the studies were also scrutinized. Ultimately, two articles were excluded for failing to meet Fink’s criteria, particularly in providing sufficient detail on methodology, results, conclusions, strengths, or limitations. The review process is illustrated in Fig.  1 .

The study selection process

2.6 Data extraction

The next step is data extraction, the process of capturing the key information and categories from the included studies. To improve efficiency, reduce variation among authors, and minimize errors in data analysis, the coding categories were constructed using Creswell's [ 15 ] coding techniques for data extraction and interpretation. The coding process involves three sequential steps. The initial stage encompasses open coding , where the researcher examines the data, generates codes to describe and categorize it, and gains a deeper understanding without preconceived ideas. Following open coding is axial coding , where the interrelationships between codes from open coding are analyzed to establish more comprehensive categories or themes. The process concludes with selective coding , refining and integrating categories or themes to identify core concepts emerging from the data. The first coder performed the coding process, then engaged in discussions with the second and third authors to finalize the coding categories for the first five articles. The first coder then proceeded to code all studies and engaged again in discussions with the other authors to ensure the finalization of the coding process. After a comprehensive analysis and capturing of the key information from the included studies, the data extraction and interpretation process yielded several themes. These themes have been categorized and are presented in Table  2 . It is important to note that open coding results were removed from Table  2 for aesthetic reasons, as it included many generic aspects, such as words, short phrases, or sentences mentioned in the studies.

2.7 Synthesize studies

In this stage, we will gather, discuss, and analyze the key findings that emerged from the selected studies. The synthesis stage is considered a transition from an author-centric to a concept-centric focus, enabling us to map all the provided information to achieve the most effective evaluation of the data [ 87 ]. Initially, the authors extracted data that included general information about the selected studies, including the author(s)' names, study titles, years of publication, educational levels, research methodologies, sample sizes, participants, main aims or objectives, raw data sources, and analysis methods. Following that, all key information and significant results from the selected studies were compiled using Creswell’s [ 15 ] coding techniques for data extraction and interpretation to identify core concepts and themes emerging from the data, focusing on those that directly contributed to our research questions and objectives, such as the initial utilization of ChatGPT in learning and teaching, learners' and educators' familiarity with ChatGPT, and the main findings of each study. Finally, the data related to each selected study were extracted into an Excel spreadsheet for data processing. The Excel spreadsheet was reviewed by the authors, including a series of discussions to ensure the finalization of this process and prepare it for further analysis. Afterward, the final result being analyzed and presented in various types of charts and graphs. Table 4 presents the extracted data from the selected studies, with each study labeled with a capital 'S' followed by a number.

This section consists of two main parts. The first part provides a descriptive analysis of the data compiled from the reviewed studies. The second part presents the answers to the research questions and the main findings of these studies.

3.1 Part 1: descriptive analysis

This section will provide a descriptive analysis of the reviewed studies, including educational levels and fields, participants distribution, country contribution, research methodologies, study sample size, study population, publication year, list of journals, familiarity with ChatGPT, source of data, and the main aims and objectives of the studies. Table 4 presents a comprehensive overview of the extracted data from the selected studies.

3.1.1 The number of the reviewed studies and publication years

The total number of the reviewed studies was 14. All studies were empirical studies and published in different journals focusing on Education and Technology. One study was published in 2022 [S1], while the remaining were published in 2023 [S2]-[S14]. Table 3 illustrates the year of publication, the names of the journals, and the number of reviewed studies published in each journal for the studies reviewed.

3.1.2 Educational levels and fields

The majority of the reviewed studies, 11 studies, were conducted in higher education institutions [S1]-[S10] and [S13]. Two studies did not specify the educational level of the population [S12] and [S14], while one study focused on elementary education [S11]. However, the reviewed studies covered various fields of education. Three studies focused on Arts and Humanities Education [S8], [S11], and [S14], specifically English Education. Two studies focused on Engineering Education, with one in Computer Engineering [S2] and the other in Construction Education [S3]. Two studies focused on Mathematics Education [S5] and [S12]. One study focused on Social Science Education [S13]. One study focused on Early Education [S4]. One study focused on Journalism Education [S9]. Finally, three studies did not specify the field of education [S1], [S6], and [S7]. Figure  2 represents the educational levels in the reviewed studies, while Fig.  3 represents the context of the reviewed studies.

Educational levels in the reviewed studies

Context of the reviewed studies

3.1.3 Participants distribution and countries contribution

The reviewed studies have been conducted across different geographic regions, providing a diverse representation of the studies. The majority of the studies, 10 in total, [S1]-[S3], [S5]-[S9], [S11], and [S14], primarily focused on participants from single countries such as Pakistan, the United Arab Emirates, China, Indonesia, Poland, Saudi Arabia, South Korea, Spain, Tajikistan, and the United States. In contrast, four studies, [S4], [S10], [S12], and [S13], involved participants from multiple countries, including China and the United States [S4], China, the United Kingdom, and the United States [S10], the United Arab Emirates, Oman, Saudi Arabia, and Jordan [S12], Turkey, Sweden, Canada, and Australia [ 13 ]. Figures  4 and 5 illustrate the distribution of participants, whether from single or multiple countries, and the contribution of each country in the reviewed studies, respectively.

The reviewed studies conducted in single or multiple countries

The Contribution of each country in the studies

3.1.4 Study population and sample size

Four study populations were included: university students, university teachers, university teachers and students, and elementary school teachers. Six studies involved university students [S2], [S3], [S5] and [S6]-[S8]. Three studies focused on university teachers [S1], [S4], and [S6], while one study specifically targeted elementary school teachers [S11]. Additionally, four studies included both university teachers and students [S10] and [ 12 , 13 , 14 ], and among them, study [S13] specifically included postgraduate students. In terms of the sample size of the reviewed studies, nine studies included a small sample size of less than 50 participants [S1], [S3], [S6], [S8], and [S10]-[S13]. Three studies had 50–100 participants [S2], [S9], and [S14]. Only one study had more than 100 participants [S7]. It is worth mentioning that study [S4] adopted a mixed methods approach, including 10 participants for qualitative analysis and 110 participants for quantitative analysis.

3.1.5 Participants’ familiarity with using ChatGPT

The reviewed studies recruited a diverse range of participants with varying levels of familiarity with ChatGPT. Five studies [S2], [S4], [S6], [S8], and [S12] involved participants already familiar with ChatGPT, while eight studies [S1], [S3], [S5], [S7], [S9], [S10], [S13] and [S14] included individuals with differing levels of familiarity. Notably, one study [S11] had participants who were entirely unfamiliar with ChatGPT. It is important to note that four studies [S3], [S5], [S9], and [S11] provided training or guidance to their participants before conducting their studies, while ten studies [S1], [S2], [S4], [S6]-[S8], [S10], and [S12]-[S14] did not provide training due to the participants' existing familiarity with ChatGPT.

3.1.6 Research methodology approaches and source(S) of data

The reviewed studies adopted various research methodology approaches. Seven studies adopted qualitative research methodology [S1], [S4], [S6], [S8], [S10], [S11], and [S12], while three studies adopted quantitative research methodology [S3], [S7], and [S14], and four studies employed mixed-methods, which involved a combination of both the strengths of qualitative and quantitative methods [S2], [S5], [S9], and [S13].

In terms of the source(s) of data, the reviewed studies obtained their data from various sources, such as interviews, questionnaires, and pre-and post-tests. Six studies relied on interviews as their primary source of data collection [S1], [S4], [S6], [S10], [S11], and [S12], four studies relied on questionnaires [S2], [S7], [S13], and [S14], two studies combined the use of pre-and post-tests and questionnaires for data collection [S3] and [S9], while two studies combined the use of questionnaires and interviews to obtain the data [S5] and [S8]. It is important to note that six of the reviewed studies were quasi-experimental [S3], [S5], [S8], [S9], [S12], and [S14], while the remaining ones were experimental studies [S1], [S2], [S4], [S6], [S7], [S10], [S11], and [S13]. Figures  6 and 7 illustrate the research methodologies and the source (s) of data used in the reviewed studies, respectively.

Research methodologies in the reviewed studies

Source of data in the reviewed studies

3.1.7 The aim and objectives of the studies

The reviewed studies encompassed a diverse set of aims, with several of them incorporating multiple primary objectives. Six studies [S3], [S6], [S7], [S8], [S11], and [S12] examined the integration of ChatGPT in educational contexts, and four studies [S4], [S5], [S13], and [S14] investigated the various implications of its use in education, while three studies [S2], [S9], and [S10] aimed to explore both its integration and implications in education. Additionally, seven studies explicitly explored attitudes and perceptions of students [S2] and [S3], educators [S1] and [S6], or both [S10], [S12], and [S13] regarding the utilization of ChatGPT in educational settings.

3.2 Part 2: research questions and main findings of the reviewed studies

This part will present the answers to the research questions and the main findings of the reviewed studies, classified into two main categories (learning and teaching) according to AI Education classification by [ 36 ]. Figure  8 summarizes the main findings of the reviewed studies in a visually informative diagram. Table 4 provides a detailed list of the key information extracted from the selected studies that led to generating these themes.

The main findings in the reviewed studies

4 Students' initial attempts at utilizing ChatGPT in learning and main findings from students' perspective

4.1 virtual intelligent assistant.

Nine studies demonstrated that ChatGPT has been utilized by students as an intelligent assistant to enhance and support their learning. Students employed it for various purposes, such as answering on-demand questions [S2]-[S5], [S8], [S10], and [S12], providing valuable information and learning resources [S2]-[S5], [S6], and [S8], as well as receiving immediate feedback [S2], [S4], [S9], [S10], and [S12]. In this regard, students generally were confident in the accuracy of ChatGPT's responses, considering them relevant, reliable, and detailed [S3], [S4], [S5], and [S8]. However, some students indicated the need for improvement, as they found that answers are not always accurate [S2], and that misleading information may have been provided or that it may not always align with their expectations [S6] and [S10]. It was also observed by the students that the accuracy of ChatGPT is dependent on several factors, including the quality and specificity of the user's input, the complexity of the question or topic, and the scope and relevance of its training data [S12]. Many students felt that ChatGPT's answers were not always accurate and most of them believed that it requires good background knowledge to work with.

4.2 Writing and language proficiency assistant

Six of the reviewed studies highlighted that ChatGPT has been utilized by students as a valuable assistant tool to improve their academic writing skills and language proficiency. Among these studies, three mainly focused on English education, demonstrating that students showed sufficient mastery in using ChatGPT for generating ideas, summarizing, paraphrasing texts, and completing writing essays [S8], [S11], and [S14]. Furthermore, ChatGPT helped them in writing by making students active investigators rather than passive knowledge recipients and facilitated the development of their writing skills [S11] and [S14]. Similarly, ChatGPT allowed students to generate unique ideas and perspectives, leading to deeper analysis and reflection on their journalism writing [S9]. In terms of language proficiency, ChatGPT allowed participants to translate content into their home languages, making it more accessible and relevant to their context [S4]. It also enabled them to request changes in linguistic tones or flavors [S8]. Moreover, participants used it to check grammar or as a dictionary [S11].

4.3 Valuable resource for learning approaches

Five studies demonstrated that students used ChatGPT as a valuable complementary resource for self-directed learning. It provided learning resources and guidance on diverse educational topics and created a supportive home learning environment [S2] and [S4]. Moreover, it offered step-by-step guidance to grasp concepts at their own pace and enhance their understanding [S5], streamlined task and project completion carried out independently [S7], provided comprehensive and easy-to-understand explanations on various subjects [S10], and assisted in studying geometry operations, thereby empowering them to explore geometry operations at their own pace [S12]. Three studies showed that students used ChatGPT as a valuable learning resource for personalized learning. It delivered age-appropriate conversations and tailored teaching based on a child's interests [S4], acted as a personalized learning assistant, adapted to their needs and pace, which assisted them in understanding mathematical concepts [S12], and enabled personalized learning experiences in social sciences by adapting to students' needs and learning styles [S13]. On the other hand, it is important to note that, according to one study [S5], students suggested that using ChatGPT may negatively affect collaborative learning competencies between students.

4.4 Enhancing students' competencies

Six of the reviewed studies have shown that ChatGPT is a valuable tool for improving a wide range of skills among students. Two studies have provided evidence that ChatGPT led to improvements in students' critical thinking, reasoning skills, and hazard recognition competencies through engaging them in interactive conversations or activities and providing responses related to their disciplines in journalism [S5] and construction education [S9]. Furthermore, two studies focused on mathematical education have shown the positive impact of ChatGPT on students' problem-solving abilities in unraveling problem-solving questions [S12] and enhancing the students' understanding of the problem-solving process [S5]. Lastly, one study indicated that ChatGPT effectively contributed to the enhancement of conversational social skills [S4].

4.5 Supporting students' academic success

Seven of the reviewed studies highlighted that students found ChatGPT to be beneficial for learning as it enhanced learning efficiency and improved the learning experience. It has been observed to improve students' efficiency in computer engineering studies by providing well-structured responses and good explanations [S2]. Additionally, students found it extremely useful for hazard reporting [S3], and it also enhanced their efficiency in solving mathematics problems and capabilities [S5] and [S12]. Furthermore, by finding information, generating ideas, translating texts, and providing alternative questions, ChatGPT aided students in deepening their understanding of various subjects [S6]. It contributed to an increase in students' overall productivity [S7] and improved efficiency in composing written tasks [S8]. Regarding learning experiences, ChatGPT was instrumental in assisting students in identifying hazards that they might have otherwise overlooked [S3]. It also improved students' learning experiences in solving mathematics problems and developing abilities [S5] and [S12]. Moreover, it increased students' successful completion of important tasks in their studies [S7], particularly those involving average difficulty writing tasks [S8]. Additionally, ChatGPT increased the chances of educational success by providing students with baseline knowledge on various topics [S10].

5 Teachers' initial attempts at utilizing ChatGPT in teaching and main findings from teachers' perspective

5.1 valuable resource for teaching.

The reviewed studies showed that teachers have employed ChatGPT to recommend, modify, and generate diverse, creative, organized, and engaging educational contents, teaching materials, and testing resources more rapidly [S4], [S6], [S10] and [S11]. Additionally, teachers experienced increased productivity as ChatGPT facilitated quick and accurate responses to questions, fact-checking, and information searches [S1]. It also proved valuable in constructing new knowledge [S6] and providing timely answers to students' questions in classrooms [S11]. Moreover, ChatGPT enhanced teachers' efficiency by generating new ideas for activities and preplanning activities for their students [S4] and [S6], including interactive language game partners [S11].

5.2 Improving productivity and efficiency

The reviewed studies showed that participants' productivity and work efficiency have been significantly enhanced by using ChatGPT as it enabled them to allocate more time to other tasks and reduce their overall workloads [S6], [S10], [S11], [S13], and [S14]. However, three studies [S1], [S4], and [S11], indicated a negative perception and attitude among teachers toward using ChatGPT. This negativity stemmed from a lack of necessary skills to use it effectively [S1], a limited familiarity with it [S4], and occasional inaccuracies in the content provided by it [S10].

5.3 Catalyzing new teaching methodologies

Five of the reviewed studies highlighted that educators found the necessity of redefining their teaching profession with the assistance of ChatGPT [S11], developing new effective learning strategies [S4], and adapting teaching strategies and methodologies to ensure the development of essential skills for future engineers [S5]. They also emphasized the importance of adopting new educational philosophies and approaches that can evolve with the introduction of ChatGPT into the classroom [S12]. Furthermore, updating curricula to focus on improving human-specific features, such as emotional intelligence, creativity, and philosophical perspectives [S13], was found to be essential.

5.4 Effective utilization of CHATGPT in teaching

According to the reviewed studies, effective utilization of ChatGPT in education requires providing teachers with well-structured training, support, and adequate background on how to use ChatGPT responsibly [S1], [S3], [S11], and [S12]. Establishing clear rules and regulations regarding its usage is essential to ensure it positively impacts the teaching and learning processes, including students' skills [S1], [S4], [S5], [S8], [S9], and [S11]-[S14]. Moreover, conducting further research and engaging in discussions with policymakers and stakeholders is indeed crucial for the successful integration of ChatGPT in education and to maximize the benefits for both educators and students [S1], [S6]-[S10], and [S12]-[S14].

6 Discussion

The purpose of this review is to conduct a systematic review of empirical studies that have explored the utilization of ChatGPT, one of today’s most advanced LLM-based chatbots, in education. The findings of the reviewed studies showed several ways of ChatGPT utilization in different learning and teaching practices as well as it provided insights and considerations that can facilitate its effective and responsible use in future educational contexts. The results of the reviewed studies came from diverse fields of education, which helped us avoid a biased review that is limited to a specific field. Similarly, the reviewed studies have been conducted across different geographic regions. This kind of variety in geographic representation enriched the findings of this review.

In response to RQ1 , "What are students' and teachers' initial attempts at utilizing ChatGPT in education?", the findings from this review provide comprehensive insights. Chatbots, including ChatGPT, play a crucial role in supporting student learning, enhancing their learning experiences, and facilitating diverse learning approaches [ 42 , 43 ]. This review found that this tool, ChatGPT, has been instrumental in enhancing students' learning experiences by serving as a virtual intelligent assistant, providing immediate feedback, on-demand answers, and engaging in educational conversations. Additionally, students have benefited from ChatGPT’s ability to generate ideas, compose essays, and perform tasks like summarizing, translating, paraphrasing texts, or checking grammar, thereby enhancing their writing and language competencies. Furthermore, students have turned to ChatGPT for assistance in understanding concepts and homework, providing structured learning plans, and clarifying assignments and tasks, which fosters a supportive home learning environment, allowing them to take responsibility for their own learning and cultivate the skills and approaches essential for supportive home learning environment [ 26 , 27 , 28 ]. This finding aligns with the study of Saqr et al. [ 68 , 69 ] who highlighted that, when students actively engage in their own learning process, it yields additional advantages, such as heightened motivation, enhanced achievement, and the cultivation of enthusiasm, turning them into advocates for their own learning.

Moreover, students have utilized ChatGPT for tailored teaching and step-by-step guidance on diverse educational topics, streamlining task and project completion, and generating and recommending educational content. This personalization enhances the learning environment, leading to increased academic success. This finding aligns with other recent studies [ 26 , 27 , 28 , 60 , 66 ] which revealed that ChatGPT has the potential to offer personalized learning experiences and support an effective learning process by providing students with customized feedback and explanations tailored to their needs and abilities. Ultimately, fostering students' performance, engagement, and motivation, leading to increase students' academic success [ 14 , 44 , 58 ]. This ultimate outcome is in line with the findings of Saqr et al. [ 68 , 69 ], which emphasized that learning strategies are important catalysts of students' learning, as students who utilize effective learning strategies are more likely to have better academic achievement.

Teachers, too, have capitalized on ChatGPT's capabilities to enhance productivity and efficiency, using it for creating lesson plans, generating quizzes, providing additional resources, generating and preplanning new ideas for activities, and aiding in answering students’ questions. This adoption of technology introduces new opportunities to support teaching and learning practices, enhancing teacher productivity. This finding aligns with those of Day [ 17 ], De Castro [ 18 ], and Su and Yang [ 74 ] as well as with those of Valtonen et al. [ 82 ], who revealed that emerging technological advancements have opened up novel opportunities and means to support teaching and learning practices, and enhance teachers’ productivity.

In response to RQ2 , "What are the main findings derived from empirical studies that have incorporated ChatGPT into learning and teaching?", the findings from this review provide profound insights and raise significant concerns. Starting with the insights, chatbots, including ChatGPT, have demonstrated the potential to reshape and revolutionize education, creating new, novel opportunities for enhancing the learning process and outcomes [ 83 ], facilitating different learning approaches, and offering a range of pedagogical benefits [ 19 , 43 , 72 ]. In this context, this review found that ChatGPT could open avenues for educators to adopt or develop new effective learning and teaching strategies that can evolve with the introduction of ChatGPT into the classroom. Nonetheless, there is an evident lack of research understanding regarding the potential impact of generative machine learning models within diverse educational settings [ 83 ]. This necessitates teachers to attain a high level of proficiency in incorporating chatbots, such as ChatGPT, into their classrooms to create inventive, well-structured, and captivating learning strategies. In the same vein, the review also found that teachers without the requisite skills to utilize ChatGPT realized that it did not contribute positively to their work and could potentially have adverse effects [ 37 ]. This concern could lead to inequity of access to the benefits of chatbots, including ChatGPT, as individuals who lack the necessary expertise may not be able to harness their full potential, resulting in disparities in educational outcomes and opportunities. Therefore, immediate action is needed to address these potential issues. A potential solution is offering training, support, and competency development for teachers to ensure that all of them can leverage chatbots, including ChatGPT, effectively and equitably in their educational practices [ 5 , 28 , 80 ], which could enhance accessibility and inclusivity, and potentially result in innovative outcomes [ 82 , 83 ].

Additionally, chatbots, including ChatGPT, have the potential to significantly impact students' thinking abilities, including retention, reasoning, analysis skills [ 19 , 45 ], and foster innovation and creativity capabilities [ 83 ]. This review found that ChatGPT could contribute to improving a wide range of skills among students. However, it found that frequent use of ChatGPT may result in a decrease in innovative capacities, collaborative skills and cognitive capacities, and students' motivation to attend classes, as well as could lead to reduced higher-order thinking skills among students [ 22 , 29 ]. Therefore, immediate action is needed to carefully examine the long-term impact of chatbots such as ChatGPT, on learning outcomes as well as to explore its incorporation into educational settings as a supportive tool without compromising students' cognitive development and critical thinking abilities. In the same vein, the review also found that it is challenging to draw a consistent conclusion regarding the potential of ChatGPT to aid self-directed learning approach. This finding aligns with the recent study of Baskara [ 8 ]. Therefore, further research is needed to explore the potential of ChatGPT for self-directed learning. One potential solution involves utilizing learning analytics as a novel approach to examine various aspects of students' learning and support them in their individual endeavors [ 32 ]. This approach can bridge this gap by facilitating an in-depth analysis of how learners engage with ChatGPT, identifying trends in self-directed learning behavior, and assessing its influence on their outcomes.

Turning to the significant concerns, on the other hand, a fundamental challenge with LLM-based chatbots, including ChatGPT, is the accuracy and quality of the provided information and responses, as they provide false information as truth—a phenomenon often referred to as "hallucination" [ 3 , 49 ]. In this context, this review found that the provided information was not entirely satisfactory. Consequently, the utilization of chatbots presents potential concerns, such as generating and providing inaccurate or misleading information, especially for students who utilize it to support their learning. This finding aligns with other findings [ 6 , 30 , 35 , 40 ] which revealed that incorporating chatbots such as ChatGPT, into education presents challenges related to its accuracy and reliability due to its training on a large corpus of data, which may contain inaccuracies and the way users formulate or ask ChatGPT. Therefore, immediate action is needed to address these potential issues. One possible solution is to equip students with the necessary skills and competencies, which include a background understanding of how to use it effectively and the ability to assess and evaluate the information it generates, as the accuracy and the quality of the provided information depend on the input, its complexity, the topic, and the relevance of its training data [ 28 , 49 , 86 ]. However, it's also essential to examine how learners can be educated about how these models operate, the data used in their training, and how to recognize their limitations, challenges, and issues [ 79 ].

Furthermore, chatbots present a substantial challenge concerning maintaining academic integrity [ 20 , 56 ] and copyright violations [ 83 ], which are significant concerns in education. The review found that the potential misuse of ChatGPT might foster cheating, facilitate plagiarism, and threaten academic integrity. This issue is also affirmed by the research conducted by Basic et al. [ 7 ], who presented evidence that students who utilized ChatGPT in their writing assignments had more plagiarism cases than those who did not. These findings align with the conclusions drawn by Cotton et al. [ 13 ], Hisan and Amri [ 33 ] and Sullivan et al. [ 75 ], who revealed that the integration of chatbots such as ChatGPT into education poses a significant challenge to the preservation of academic integrity. Moreover, chatbots, including ChatGPT, have increased the difficulty in identifying plagiarism [ 47 , 67 , 76 ]. The findings from previous studies [ 1 , 84 ] indicate that AI-generated text often went undetected by plagiarism software, such as Turnitin. However, Turnitin and other similar plagiarism detection tools, such as ZeroGPT, GPTZero, and Copyleaks, have since evolved, incorporating enhanced techniques to detect AI-generated text, despite the possibility of false positives, as noted in different studies that have found these tools still not yet fully ready to accurately and reliably identify AI-generated text [ 10 , 51 ], and new novel detection methods may need to be created and implemented for AI-generated text detection [ 4 ]. This potential issue could lead to another concern, which is the difficulty of accurately evaluating student performance when they utilize chatbots such as ChatGPT assistance in their assignments. Consequently, the most LLM-driven chatbots present a substantial challenge to traditional assessments [ 64 ]. The findings from previous studies indicate the importance of rethinking, improving, and redesigning innovative assessment methods in the era of chatbots [ 14 , 20 , 64 , 75 ]. These methods should prioritize the process of evaluating students' ability to apply knowledge to complex cases and demonstrate comprehension, rather than solely focusing on the final product for assessment. Therefore, immediate action is needed to address these potential issues. One possible solution would be the development of clear guidelines, regulatory policies, and pedagogical guidance. These measures would help regulate the proper and ethical utilization of chatbots, such as ChatGPT, and must be established before their introduction to students [ 35 , 38 , 39 , 41 , 89 ].

In summary, our review has delved into the utilization of ChatGPT, a prominent example of chatbots, in education, addressing the question of how ChatGPT has been utilized in education. However, there remain significant gaps, which necessitate further research to shed light on this area.

7 Conclusions

This systematic review has shed light on the varied initial attempts at incorporating ChatGPT into education by both learners and educators, while also offering insights and considerations that can facilitate its effective and responsible use in future educational contexts. From the analysis of 14 selected studies, the review revealed the dual-edged impact of ChatGPT in educational settings. On the positive side, ChatGPT significantly aided the learning process in various ways. Learners have used it as a virtual intelligent assistant, benefiting from its ability to provide immediate feedback, on-demand answers, and easy access to educational resources. Additionally, it was clear that learners have used it to enhance their writing and language skills, engaging in practices such as generating ideas, composing essays, and performing tasks like summarizing, translating, paraphrasing texts, or checking grammar. Importantly, other learners have utilized it in supporting and facilitating their directed and personalized learning on a broad range of educational topics, assisting in understanding concepts and homework, providing structured learning plans, and clarifying assignments and tasks. Educators, on the other hand, found ChatGPT beneficial for enhancing productivity and efficiency. They used it for creating lesson plans, generating quizzes, providing additional resources, and answers learners' questions, which saved time and allowed for more dynamic and engaging teaching strategies and methodologies.

However, the review also pointed out negative impacts. The results revealed that overuse of ChatGPT could decrease innovative capacities and collaborative learning among learners. Specifically, relying too much on ChatGPT for quick answers can inhibit learners' critical thinking and problem-solving skills. Learners might not engage deeply with the material or consider multiple solutions to a problem. This tendency was particularly evident in group projects, where learners preferred consulting ChatGPT individually for solutions over brainstorming and collaborating with peers, which negatively affected their teamwork abilities. On a broader level, integrating ChatGPT into education has also raised several concerns, including the potential for providing inaccurate or misleading information, issues of inequity in access, challenges related to academic integrity, and the possibility of misusing the technology.

Accordingly, this review emphasizes the urgency of developing clear rules, policies, and regulations to ensure ChatGPT's effective and responsible use in educational settings, alongside other chatbots, by both learners and educators. This requires providing well-structured training to educate them on responsible usage and understanding its limitations, along with offering sufficient background information. Moreover, it highlights the importance of rethinking, improving, and redesigning innovative teaching and assessment methods in the era of ChatGPT. Furthermore, conducting further research and engaging in discussions with policymakers and stakeholders are essential steps to maximize the benefits for both educators and learners and ensure academic integrity.

It is important to acknowledge that this review has certain limitations. Firstly, the limited inclusion of reviewed studies can be attributed to several reasons, including the novelty of the technology, as new technologies often face initial skepticism and cautious adoption; the lack of clear guidelines or best practices for leveraging this technology for educational purposes; and institutional or governmental policies affecting the utilization of this technology in educational contexts. These factors, in turn, have affected the number of studies available for review. Secondly, the utilization of the original version of ChatGPT, based on GPT-3 or GPT-3.5, implies that new studies utilizing the updated version, GPT-4 may lead to different findings. Therefore, conducting follow-up systematic reviews is essential once more empirical studies on ChatGPT are published. Additionally, long-term studies are necessary to thoroughly examine and assess the impact of ChatGPT on various educational practices.

Despite these limitations, this systematic review has highlighted the transformative potential of ChatGPT in education, revealing its diverse utilization by learners and educators alike and summarized the benefits of incorporating it into education, as well as the forefront critical concerns and challenges that must be addressed to facilitate its effective and responsible use in future educational contexts. This review could serve as an insightful resource for practitioners who seek to integrate ChatGPT into education and stimulate further research in the field.

Data availability

The data supporting our findings are available upon request.

Abbreviations

• Artificial intelligence

AI in education

Large language model

Artificial neural networks

Chat Generative Pre-Trained Transformer

Recurrent neural networks

Long short-term memory

Reinforcement learning from human feedback

Natural language processing

Preferred Reporting Items for Systematic Reviews and Meta-Analyses

AlAfnan MA, Dishari S, Jovic M, Lomidze K. ChatGPT as an educational tool: opportunities, challenges, and recommendations for communication, business writing, and composition courses. J Artif Intell Technol. 2023. https://doi.org/10.37965/jait.2023.0184 .

Article   Google Scholar  

Ali JKM, Shamsan MAA, Hezam TA, Mohammed AAQ. Impact of ChatGPT on learning motivation. J Engl Stud Arabia Felix. 2023;2(1):41–9. https://doi.org/10.56540/jesaf.v2i1.51 .

Alkaissi H, McFarlane SI. Artificial hallucinations in ChatGPT: implications in scientific writing. Cureus. 2023. https://doi.org/10.7759/cureus.35179 .

Anderson N, Belavý DL, Perle SM, Hendricks S, Hespanhol L, Verhagen E, Memon AR. AI did not write this manuscript, or did it? Can we trick the AI text detector into generated texts? The potential future of ChatGPT and AI in sports & exercise medicine manuscript generation. BMJ Open Sport Exerc Med. 2023;9(1): e001568. https://doi.org/10.1136/bmjsem-2023-001568 .

Ausat AMA, Massang B, Efendi M, Nofirman N, Riady Y. Can chat GPT replace the role of the teacher in the classroom: a fundamental analysis. J Educ. 2023;5(4):16100–6.

Google Scholar  

Baidoo-Anu D, Ansah L. Education in the Era of generative artificial intelligence (AI): understanding the potential benefits of ChatGPT in promoting teaching and learning. Soc Sci Res Netw. 2023. https://doi.org/10.2139/ssrn.4337484 .

Basic Z, Banovac A, Kruzic I, Jerkovic I. Better by you, better than me, chatgpt3 as writing assistance in students essays. 2023. arXiv preprint arXiv:2302.04536 .‏

Baskara FR. The promises and pitfalls of using chat GPT for self-determined learning in higher education: an argumentative review. Prosiding Seminar Nasional Fakultas Tarbiyah dan Ilmu Keguruan IAIM Sinjai. 2023;2:95–101. https://doi.org/10.47435/sentikjar.v2i0.1825 .

Behera RK, Bala PK, Dhir A. The emerging role of cognitive computing in healthcare: a systematic literature review. Int J Med Inform. 2019;129:154–66. https://doi.org/10.1016/j.ijmedinf.2019.04.024 .

Chaka C. Detecting AI content in responses generated by ChatGPT, YouChat, and Chatsonic: the case of five AI content detection tools. J Appl Learn Teach. 2023. https://doi.org/10.37074/jalt.2023.6.2.12 .

Chiu TKF, Xia Q, Zhou X, Chai CS, Cheng M. Systematic literature review on opportunities, challenges, and future research recommendations of artificial intelligence in education. Comput Educ Artif Intell. 2023;4:100118. https://doi.org/10.1016/j.caeai.2022.100118 .

Choi EPH, Lee JJ, Ho M, Kwok JYY, Lok KYW. Chatting or cheating? The impacts of ChatGPT and other artificial intelligence language models on nurse education. Nurse Educ Today. 2023;125:105796. https://doi.org/10.1016/j.nedt.2023.105796 .

Cotton D, Cotton PA, Shipway JR. Chatting and cheating: ensuring academic integrity in the era of ChatGPT. Innov Educ Teach Int. 2023. https://doi.org/10.1080/14703297.2023.2190148 .

Crawford J, Cowling M, Allen K. Leadership is needed for ethical ChatGPT: Character, assessment, and learning using artificial intelligence (AI). J Univ Teach Learn Pract. 2023. https://doi.org/10.53761/1.20.3.02 .

Creswell JW. Educational research: planning, conducting, and evaluating quantitative and qualitative research [Ebook]. 4th ed. London: Pearson Education; 2015.

Curry D. ChatGPT Revenue and Usage Statistics (2023)—Business of Apps. 2023. https://www.businessofapps.com/data/chatgpt-statistics/

Day T. A preliminary investigation of fake peer-reviewed citations and references generated by ChatGPT. Prof Geogr. 2023. https://doi.org/10.1080/00330124.2023.2190373 .

De Castro CA. A Discussion about the Impact of ChatGPT in education: benefits and concerns. J Bus Theor Pract. 2023;11(2):p28. https://doi.org/10.22158/jbtp.v11n2p28 .

Deng X, Yu Z. A meta-analysis and systematic review of the effect of Chatbot technology use in sustainable education. Sustainability. 2023;15(4):2940. https://doi.org/10.3390/su15042940 .

Eke DO. ChatGPT and the rise of generative AI: threat to academic integrity? J Responsib Technol. 2023;13:100060. https://doi.org/10.1016/j.jrt.2023.100060 .

Elmoazen R, Saqr M, Tedre M, Hirsto L. A systematic literature review of empirical research on epistemic network analysis in education. IEEE Access. 2022;10:17330–48. https://doi.org/10.1109/access.2022.3149812 .

Farrokhnia M, Banihashem SK, Noroozi O, Wals AEJ. A SWOT analysis of ChatGPT: implications for educational practice and research. Innov Educ Teach Int. 2023. https://doi.org/10.1080/14703297.2023.2195846 .

Fergus S, Botha M, Ostovar M. Evaluating academic answers generated using ChatGPT. J Chem Educ. 2023;100(4):1672–5. https://doi.org/10.1021/acs.jchemed.3c00087 .

Fink A. Conducting research literature reviews: from the Internet to Paper. Incorporated: SAGE Publications; 2010.

Firaina R, Sulisworo D. Exploring the usage of ChatGPT in higher education: frequency and impact on productivity. Buletin Edukasi Indonesia (BEI). 2023;2(01):39–46. https://doi.org/10.56741/bei.v2i01.310 .

Firat, M. (2023). How chat GPT can transform autodidactic experiences and open education.  Department of Distance Education, Open Education Faculty, Anadolu Unive .‏ https://orcid.org/0000-0001-8707-5918

Firat M. What ChatGPT means for universities: perceptions of scholars and students. J Appl Learn Teach. 2023. https://doi.org/10.37074/jalt.2023.6.1.22 .

Fuchs K. Exploring the opportunities and challenges of NLP models in higher education: is Chat GPT a blessing or a curse? Front Educ. 2023. https://doi.org/10.3389/feduc.2023.1166682 .

García-Peñalvo FJ. La percepción de la inteligencia artificial en contextos educativos tras el lanzamiento de ChatGPT: disrupción o pánico. Educ Knowl Soc. 2023;24: e31279. https://doi.org/10.14201/eks.31279 .

Gilson A, Safranek CW, Huang T, Socrates V, Chi L, Taylor A, Chartash D. How does ChatGPT perform on the United States medical Licensing examination? The implications of large language models for medical education and knowledge assessment. JMIR Med Educ. 2023;9: e45312. https://doi.org/10.2196/45312 .

Hashana AJ, Brundha P, Ayoobkhan MUA, Fazila S. Deep Learning in ChatGPT—A Survey. In   2023 7th international conference on trends in electronics and informatics (ICOEI) . 2023. (pp. 1001–1005). IEEE. https://doi.org/10.1109/icoei56765.2023.10125852

Hirsto L, Saqr M, López-Pernas S, Valtonen T. (2022). A systematic narrative review of learning analytics research in K-12 and schools.  Proceedings . https://ceur-ws.org/Vol-3383/FLAIEC22_paper_9536.pdf

Hisan UK, Amri MM. ChatGPT and medical education: a double-edged sword. J Pedag Educ Sci. 2023;2(01):71–89. https://doi.org/10.13140/RG.2.2.31280.23043/1 .

Hopkins AM, Logan JM, Kichenadasse G, Sorich MJ. Artificial intelligence chatbots will revolutionize how cancer patients access information: ChatGPT represents a paradigm-shift. JNCI Cancer Spectr. 2023. https://doi.org/10.1093/jncics/pkad010 .

Househ M, AlSaad R, Alhuwail D, Ahmed A, Healy MG, Latifi S, Sheikh J. Large Language models in medical education: opportunities, challenges, and future directions. JMIR Med Educ. 2023;9: e48291. https://doi.org/10.2196/48291 .

Ilkka T. The impact of artificial intelligence on learning, teaching, and education. Minist de Educ. 2018. https://doi.org/10.2760/12297 .

Iqbal N, Ahmed H, Azhar KA. Exploring teachers’ attitudes towards using CHATGPT. Globa J Manag Adm Sci. 2022;3(4):97–111. https://doi.org/10.46568/gjmas.v3i4.163 .

Irfan M, Murray L, Ali S. Integration of Artificial intelligence in academia: a case study of critical teaching and learning in Higher education. Globa Soc Sci Rev. 2023;8(1):352–64. https://doi.org/10.31703/gssr.2023(viii-i).32 .

Jeon JH, Lee S. Large language models in education: a focus on the complementary relationship between human teachers and ChatGPT. Educ Inf Technol. 2023. https://doi.org/10.1007/s10639-023-11834-1 .

Khan RA, Jawaid M, Khan AR, Sajjad M. ChatGPT—Reshaping medical education and clinical management. Pak J Med Sci. 2023. https://doi.org/10.12669/pjms.39.2.7653 .

King MR. A conversation on artificial intelligence, Chatbots, and plagiarism in higher education. Cell Mol Bioeng. 2023;16(1):1–2. https://doi.org/10.1007/s12195-022-00754-8 .

Kooli C. Chatbots in education and research: a critical examination of ethical implications and solutions. Sustainability. 2023;15(7):5614. https://doi.org/10.3390/su15075614 .

Kuhail MA, Alturki N, Alramlawi S, Alhejori K. Interacting with educational chatbots: a systematic review. Educ Inf Technol. 2022;28(1):973–1018. https://doi.org/10.1007/s10639-022-11177-3 .

Lee H. The rise of ChatGPT: exploring its potential in medical education. Anat Sci Educ. 2023. https://doi.org/10.1002/ase.2270 .

Li L, Subbareddy R, Raghavendra CG. AI intelligence Chatbot to improve students learning in the higher education platform. J Interconnect Netw. 2022. https://doi.org/10.1142/s0219265921430325 .

Limna P. A Review of Artificial Intelligence (AI) in Education during the Digital Era. 2022. https://ssrn.com/abstract=4160798

Lo CK. What is the impact of ChatGPT on education? A rapid review of the literature. Educ Sci. 2023;13(4):410. https://doi.org/10.3390/educsci13040410 .

Luo W, He H, Liu J, Berson IR, Berson MJ, Zhou Y, Li H. Aladdin’s genie or pandora’s box For early childhood education? Experts chat on the roles, challenges, and developments of ChatGPT. Early Educ Dev. 2023. https://doi.org/10.1080/10409289.2023.2214181 .

Meyer JG, Urbanowicz RJ, Martin P, O’Connor K, Li R, Peng P, Moore JH. ChatGPT and large language models in academia: opportunities and challenges. Biodata Min. 2023. https://doi.org/10.1186/s13040-023-00339-9 .

Mhlanga D. Open AI in education, the responsible and ethical use of ChatGPT towards lifelong learning. Soc Sci Res Netw. 2023. https://doi.org/10.2139/ssrn.4354422 .

Neumann, M., Rauschenberger, M., & Schön, E. M. (2023). “We Need To Talk About ChatGPT”: The Future of AI and Higher Education.‏ https://doi.org/10.1109/seeng59157.2023.00010

Nolan B. Here are the schools and colleges that have banned the use of ChatGPT over plagiarism and misinformation fears. Business Insider . 2023. https://www.businessinsider.com

O’Leary DE. An analysis of three chatbots: BlenderBot, ChatGPT and LaMDA. Int J Intell Syst Account, Financ Manag. 2023;30(1):41–54. https://doi.org/10.1002/isaf.1531 .

Okoli C. A guide to conducting a standalone systematic literature review. Commun Assoc Inf Syst. 2015. https://doi.org/10.17705/1cais.03743 .

OpenAI. (2023). https://openai.com/blog/chatgpt

Perkins M. Academic integrity considerations of AI large language models in the post-pandemic era: ChatGPT and beyond. J Univ Teach Learn Pract. 2023. https://doi.org/10.53761/1.20.02.07 .

Plevris V, Papazafeiropoulos G, Rios AJ. Chatbots put to the test in math and logic problems: A preliminary comparison and assessment of ChatGPT-3.5, ChatGPT-4, and Google Bard. arXiv (Cornell University) . 2023. https://doi.org/10.48550/arxiv.2305.18618

Rahman MM, Watanobe Y (2023) ChatGPT for education and research: opportunities, threats, and strategies. Appl Sci 13(9):5783. https://doi.org/10.3390/app13095783

Ram B, Verma P. Artificial intelligence AI-based Chatbot study of ChatGPT, google AI bard and baidu AI. World J Adv Eng Technol Sci. 2023;8(1):258–61. https://doi.org/10.30574/wjaets.2023.8.1.0045 .

Rasul T, Nair S, Kalendra D, Robin M, de Oliveira Santini F, Ladeira WJ, Heathcote L. The role of ChatGPT in higher education: benefits, challenges, and future research directions. J Appl Learn Teach. 2023. https://doi.org/10.37074/jalt.2023.6.1.29 .

Ratnam M, Sharm B, Tomer A. ChatGPT: educational artificial intelligence. Int J Adv Trends Comput Sci Eng. 2023;12(2):84–91. https://doi.org/10.30534/ijatcse/2023/091222023 .

Ray PP. ChatGPT: a comprehensive review on background, applications, key challenges, bias, ethics, limitations and future scope. Internet Things Cyber-Phys Syst. 2023;3:121–54. https://doi.org/10.1016/j.iotcps.2023.04.003 .

Roumeliotis KI, Tselikas ND. ChatGPT and Open-AI models: a preliminary review. Future Internet. 2023;15(6):192. https://doi.org/10.3390/fi15060192 .

Rudolph J, Tan S, Tan S. War of the chatbots: Bard, Bing Chat, ChatGPT, Ernie and beyond. The new AI gold rush and its impact on higher education. J Appl Learn Teach. 2023. https://doi.org/10.37074/jalt.2023.6.1.23 .

Ruiz LMS, Moll-López S, Nuñez-Pérez A, Moraño J, Vega-Fleitas E. ChatGPT challenges blended learning methodologies in engineering education: a case study in mathematics. Appl Sci. 2023;13(10):6039. https://doi.org/10.3390/app13106039 .

Sallam M, Salim NA, Barakat M, Al-Tammemi AB. ChatGPT applications in medical, dental, pharmacy, and public health education: a descriptive study highlighting the advantages and limitations. Narra J. 2023;3(1): e103. https://doi.org/10.52225/narra.v3i1.103 .

Salvagno M, Taccone FS, Gerli AG. Can artificial intelligence help for scientific writing? Crit Care. 2023. https://doi.org/10.1186/s13054-023-04380-2 .

Saqr M, López-Pernas S, Helske S, Hrastinski S. The longitudinal association between engagement and achievement varies by time, students’ profiles, and achievement state: a full program study. Comput Educ. 2023;199:104787. https://doi.org/10.1016/j.compedu.2023.104787 .

Saqr M, Matcha W, Uzir N, Jovanović J, Gašević D, López-Pernas S. Transferring effective learning strategies across learning contexts matters: a study in problem-based learning. Australas J Educ Technol. 2023;39(3):9.

Schöbel S, Schmitt A, Benner D, Saqr M, Janson A, Leimeister JM. Charting the evolution and future of conversational agents: a research agenda along five waves and new frontiers. Inf Syst Front. 2023. https://doi.org/10.1007/s10796-023-10375-9 .

Shoufan A. Exploring students’ perceptions of CHATGPT: thematic analysis and follow-up survey. IEEE Access. 2023. https://doi.org/10.1109/access.2023.3268224 .

Sonderegger S, Seufert S. Chatbot-mediated learning: conceptual framework for the design of Chatbot use cases in education. Gallen: Institute for Educational Management and Technologies, University of St; 2022. https://doi.org/10.5220/0010999200003182 .

Book   Google Scholar  

Strzelecki A. To use or not to use ChatGPT in higher education? A study of students’ acceptance and use of technology. Interact Learn Environ. 2023. https://doi.org/10.1080/10494820.2023.2209881 .

Su J, Yang W. Unlocking the power of ChatGPT: a framework for applying generative AI in education. ECNU Rev Educ. 2023. https://doi.org/10.1177/20965311231168423 .

Sullivan M, Kelly A, McLaughlan P. ChatGPT in higher education: Considerations for academic integrity and student learning. J ApplLearn Teach. 2023;6(1):1–10. https://doi.org/10.37074/jalt.2023.6.1.17 .

Szabo A. ChatGPT is a breakthrough in science and education but fails a test in sports and exercise psychology. Balt J Sport Health Sci. 2023;1(128):25–40. https://doi.org/10.33607/bjshs.v127i4.1233 .

Taecharungroj V. “What can ChatGPT do?” analyzing early reactions to the innovative AI chatbot on Twitter. Big Data Cognit Comput. 2023;7(1):35. https://doi.org/10.3390/bdcc7010035 .

Tam S, Said RB. User preferences for ChatGPT-powered conversational interfaces versus traditional methods. Biomed Eng Soc. 2023. https://doi.org/10.58496/mjcsc/2023/004 .

Tedre M, Kahila J, Vartiainen H. (2023). Exploration on how co-designing with AI facilitates critical evaluation of ethics of AI in craft education. In: Langran E, Christensen P, Sanson J (Eds).  Proceedings of Society for Information Technology and Teacher Education International Conference . 2023. pp. 2289–2296.

Tlili A, Shehata B, Adarkwah MA, Bozkurt A, Hickey DT, Huang R, Agyemang B. What if the devil is my guardian angel: ChatGPT as a case study of using chatbots in education. Smart Learn Environ. 2023. https://doi.org/10.1186/s40561-023-00237-x .

Uddin SMJ, Albert A, Ovid A, Alsharef A. Leveraging CHATGPT to aid construction hazard recognition and support safety education and training. Sustainability. 2023;15(9):7121. https://doi.org/10.3390/su15097121 .

Valtonen T, López-Pernas S, Saqr M, Vartiainen H, Sointu E, Tedre M. The nature and building blocks of educational technology research. Comput Hum Behav. 2022;128:107123. https://doi.org/10.1016/j.chb.2021.107123 .

Vartiainen H, Tedre M. Using artificial intelligence in craft education: crafting with text-to-image generative models. Digit Creat. 2023;34(1):1–21. https://doi.org/10.1080/14626268.2023.2174557 .

Ventayen RJM. OpenAI ChatGPT generated results: similarity index of artificial intelligence-based contents. Soc Sci Res Netw. 2023. https://doi.org/10.2139/ssrn.4332664 .

Wagner MW, Ertl-Wagner BB. Accuracy of information and references using ChatGPT-3 for retrieval of clinical radiological information. Can Assoc Radiol J. 2023. https://doi.org/10.1177/08465371231171125 .

Wardat Y, Tashtoush MA, AlAli R, Jarrah AM. ChatGPT: a revolutionary tool for teaching and learning mathematics. Eurasia J Math, Sci Technol Educ. 2023;19(7):em2286. https://doi.org/10.29333/ejmste/13272 .

Webster J, Watson RT. Analyzing the past to prepare for the future: writing a literature review. Manag Inf Syst Quart. 2002;26(2):3.

Xiao Y, Watson ME. Guidance on conducting a systematic literature review. J Plan Educ Res. 2017;39(1):93–112. https://doi.org/10.1177/0739456x17723971 .

Yan D. Impact of ChatGPT on learners in a L2 writing practicum: an exploratory investigation. Educ Inf Technol. 2023. https://doi.org/10.1007/s10639-023-11742-4 .

Yu H. Reflection on whether Chat GPT should be banned by academia from the perspective of education and teaching. Front Psychol. 2023;14:1181712. https://doi.org/10.3389/fpsyg.2023.1181712 .

Zhu C, Sun M, Luo J, Li T, Wang M. How to harness the potential of ChatGPT in education? Knowl Manag ELearn. 2023;15(2):133–52. https://doi.org/10.34105/j.kmel.2023.15.008 .

Download references

The paper is co-funded by the Academy of Finland (Suomen Akatemia) Research Council for Natural Sciences and Engineering for the project Towards precision education: Idiographic learning analytics (TOPEILA), Decision Number 350560.

Author information

Authors and affiliations.

School of Computing, University of Eastern Finland, 80100, Joensuu, Finland

Yazid Albadarin, Mohammed Saqr, Nicolas Pope & Markku Tukiainen

You can also search for this author in PubMed   Google Scholar

Contributions

YA contributed to the literature search, data analysis, discussion, and conclusion. Additionally, YA contributed to the manuscript’s writing, editing, and finalization. MS contributed to the study’s design, conceptualization, acquisition of funding, project administration, allocation of resources, supervision, validation, literature search, and analysis of results. Furthermore, MS contributed to the manuscript's writing, revising, and approving it in its finalized state. NP contributed to the results, and discussions, and provided supervision. NP also contributed to the writing process, revisions, and the final approval of the manuscript in its finalized state. MT contributed to the study's conceptualization, resource management, supervision, writing, revising the manuscript, and approving it.

Corresponding author

Correspondence to Yazid Albadarin .

Ethics declarations

Competing interests.

The authors declare no competing interests.

Additional information

Publisher's note.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

See Table  4

The process of synthesizing the data presented in Table  4 involved identifying the relevant studies through a search process of databases (ERIC, Scopus, Web of Knowledge, Dimensions.ai, and lens.org) using specific keywords "ChatGPT" and "education". Following this, inclusion/exclusion criteria were applied, and data extraction was performed using Creswell's [ 15 ] coding techniques to capture key information and identify common themes across the included studies.

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ .

Reprints and permissions

About this article

Albadarin, Y., Saqr, M., Pope, N. et al. A systematic literature review of empirical research on ChatGPT in education. Discov Educ 3 , 60 (2024). https://doi.org/10.1007/s44217-024-00138-2

Download citation

Received : 22 October 2023

Accepted : 10 May 2024

Published : 26 May 2024

DOI : https://doi.org/10.1007/s44217-024-00138-2

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• Large language models
• Educational technology
• Systematic review

Advertisement

• Find a journal
• Publish with us
• Track your research

• < Previous

Home > SCRIPPS > SCRIPPS_STUDENT > SCRIPPS_THESES > 2232

Scripps Senior Theses

Improving critical thinking in written assignments: human vs. chatgpt tutor in socratic questioning intervention.

Katia Martha Follow

Graduation Year

Document type.

Open Access Senior Thesis

Degree Name

Bachelor of Arts

Jennifer Groscup

Piya Chatterjee

Tricia Morgan

Terms of Use & License Information

Terms of Use for work posted in Scholarship@Claremont .

Rights Information

2023 Katia A. Martha

The purpose of the proposed study is to trial a short Socratic Questioning (SQ) intervention in the writing process, facilitated by either a human or ChatGPT tutor, and explore the effects that this may have on students’ critical thinking (CT), which will be coded from their written responses. Participants will be undergraduate college first years in the local California area who are fluent in English and have no learning disabilities. This study involves two visits, spaced a week apart, to gather pre- and post- test data for evaluating the effectiveness of the SQ intervention in improving CT. Both visits will follow a similar format of participants taking a written exam followed by a survey, which, in visit 1, will ask about ChatGPT account set-up and participant demographics, and in visit 2, will ask about intrinsic motivation. Researchers expect that post-test CT scores will be higher in conditions with the SQ intervention as opposed to the control, and specifically higher for the SQ intervention with the human tutor versus the ChatGPT tutor. This relationship is expected to be moderated by baseline level of CT, with lower levels of baseline CT predicting greater impacts from the SQ intervention, and mediated by intrinsic motivation, where intrinsic motivation is expected to be higher for participants with the human versus ChatGPT tutor. This study will address many gaps in the literature, including how to develop and assess CT in writing, specific methods of using ChatGPT to improve student learning, comparing humans versus ChatGPT as tutors, and looking at SQ as an intervention in the writing process.

Recommended Citation

Martha, Katia, "Improving Critical Thinking in Written Assignments: Human vs. ChatGPT Tutor in Socratic Questioning Intervention" (2023). Scripps Senior Theses . 2232. https://scholarship.claremont.edu/scripps_theses/2232

Since January 16, 2024

Included in

Curriculum and Instruction Commons , Disability and Equity in Education Commons , Educational Assessment, Evaluation, and Research Commons , Educational Psychology Commons , Educational Technology Commons , Psychology Commons

Advanced Search

• Notify me via email or RSS
• Colleges, Universities, and Library
• Schools, Programs, and Departments
• Disciplines

Author Corner

• Faculty Submission
• Student Submission
• Policies and Guidelines

Useful Links

• Claremont Colleges Library
• Claremont Colleges Digital Library

Home | About | FAQ | My Account | Accessibility Statement

Privacy Copyright