Research Insights #2: Ways of Using Generative AI in Teaching & Learning
3 article reviews that give some ways of integrating generative AI
Here we go with some new research insights—created through this process I highlighted here and tested out here. I refined the prompts since the last time I did this (see post’s appendix)) and are putting them into a Google Form for my own record keeping (See appendix).
Onal, S., & Kulavuz-Onal, D. (2023). A Cross-Disciplinary Examination of the Instructional Uses of ChatGPT in Higher Education. Journal of Educational Technology Systems, 00472395231196532.
Generative AI summary:
Main Points and Suggestions: The document explores the use of ChatGPT in creating diverse educational assessment tasks across multiple disciplines in higher education. It details the process of designing multiple-choice questions, case studies, mathematical problems, and linguistic data analysis tasks using ChatGPT. The authors emphasize the potential of ChatGPT as a creative and flexible tool for generating relevant and accurate assessment materials, while also highlighting the need for human oversight to ensure the reliability and appropriateness of these materials.
Summary of Prior Discussion: Earlier discussions focused on the article's exploration of ChatGPT's applications in education, its ease of reading, evidence use, coherent argument, clarity of ideas, and diverse perspectives. It emphasized the article's innovative approaches, such as the customization of ChatGPT for educational assessments, and the importance of balancing AI outputs with human judgment. The discussions also provided insights into the article's relevance and value to educational developers.
Practices for Educational Developers:
Customizing AI-generated Content: Implement a review process to adapt AI-generated materials to specific educational contexts, ensuring relevance and accuracy.
Incorporating AI into Curriculum Development: Explore the use of ChatGPT for creating assessment tasks in diverse subjects, using it as a tool to supplement, not replace, traditional teaching methods.
Ethical Considerations and Human Oversight: Establish guidelines for ethically using AI tools, emphasizing the importance of human expertise in validating and contextualizing AI-generated content.
My Commentary
This article has some possibility and I would want to revisit it the next time I'm doing a workshop to mine it for some specific examples in disciplines that I'm less often working with but who are likely to be part of the audience. The second paragraph still needs tweaking and an improved prompt. The final paragraph is useful for folks--particularly those who may not have been engaged with or thinking about generative AI, but for some might feel a bit basic.
Singh, J., Samborowski, L., & Mentzer, K. (2023). A Human Collaboration with ChatGPT: Developing Case Studies with Generative AI. In Proceedings of the ISCAP Conference ISSN (Vol. 2473, p. 4901).
Generative AI summary:
The document, "A Human Collaboration with ChatGPT: Developing Case Studies with Generative AI," focuses on using ChatGPT to create business case studies. It examines the practicality and ethics of AI in educational content creation, particularly for MBA programs. The authors discuss the process, challenges, and opportunities of integrating ChatGPT, emphasizing detailed prompts and iterative refinement for effective use.
Throughout our discussion, we have explored the article's insights into the integration of AI in education, particularly for developing dynamic business case studies. The discussion has touched on the article's writing intention, ease of reading, evidence use, argument clarity, idea clarity, diverse perspectives, and practical application in educational settings.
For educational developers, the document suggests several practices:
Using AI like ChatGPT to generate educational content, ensuring prompts are detailed and context-specific.
Balancing AI assistance with human oversight to maintain content quality and relevance.
Addressing ethical considerations in AI use, including data privacy and responsible AI usage. To implement these, educational developers should collaborate with AI experts to understand AI capabilities and limitations, integrate AI tools into curriculum design carefully, and continually assess the ethical implications of using AI in educational contexts.
My Commentary
This piqued my interest because I have been playing around with ChatGPT's ability to create case studies in different contexts. I would probably revisit the thread to ask for the specific outline and based upon that, ask for effective prompts. Again, the second paragraph is pretty meh. The final results seem to echo the results from the first article above and my guess is something that will continue to show up in many of these articles. My question is whether it is my own wording or is just part of the contours of the genre of writing about generative AI in education.
Matthew, U. O., Bakare, K. M., Ebong, G. N., Ndukwu, C. C., & Nwanakwaugwu, A. C. (2023). Generative Artificial Intelligence (AI) Educational Pedagogy Development: Conversational AI with User-Centric ChatGPT4. Journal of Trends in Computer Science and Smart Technology, 5(4), 401-418.
Generative AI summary:
The document, "Generative Artificial Intelligence (AI) Educational Pedagogy Development: Conversational AI with User-Centric ChatGPT4," primarily discusses integrating AI, specifically ChatGPT, into educational contexts. It examines AI's role in enhancing teaching and learning methodologies, focusing on the potential of ChatGPT as a conversational agent. The article explores innovative strategies like prompt engineering and human-AI collaborative learning, addressing ethical and practical challenges of AI implementation in education.
Throughout our discussion, we've covered the article's insights on AI's integration into education, the need for prompt engineering, and the challenges of AI use in educational settings. We've discussed how AI can transform teaching and learning methods, the importance of addressing potential biases in AI, and the necessity for ongoing research in this field.
For educational developers, the document suggests several practices:
Implementing AI in teaching: Utilize AI tools like ChatGPT for personalized learning experiences and to supplement traditional teaching methods.
Ethical considerations: Be mindful of potential biases in AI and ensure its responsible use in education.
Continuous research and adaptation: Stay updated with AI advancements and adapt teaching strategies accordingly. Engage in ongoing research to explore the long-term implications of AI in education.
My Commentary
This article feels like there are some things to explore particularly exploring the idea of generative AI as "conversational agent"--that language encourages me to think the feels a bit more significant than the previous two. Skippig the second paragraph. Final considerations are still pretty much for the novice and makes me think refining that prompt might be needed going forward.
Meta-commentary
Ok, second paragraph needs reworking—there was more interesting details that didn’t quite come through.
Collectively, it seems like they all are stressing the importances of reviewing the outputs, considering the bias in AI, and the ethical considerations. That consistency is important and I wonder if that in the future that changes as well as if there are more or less robust ways that these articles address that concern.
Article 1 deals with ways of using it to create learning assessments. Article 2 is interested in content creation. Article 3 focuses on the idea of generative AI as a chat-partner for learning. Together, they represent 3 different means of using generative AI within the educational context that educational developers and faculty may find valuable for sense-making or inspiration.
Appendix
As I mentioned, I updated the prompts to get better results. Clearly, they still need work. One interesting thing that I had to work on in just the prompt. If the prompt was a paragraph with all the things needed; it put out lesser quality outputs than if I broke down the requests in a prompt into specific line breaks.
Prompt #1: Scoring the article
Assess the quality of the article. On a 10 scale (10 being the strongest), rate and explain the following aspects of the article. Think deeply about and consider that this is primarily for the benefit of educational developers.
You must draw upon and share specific details of the article:
Writing Intention: Indicate what kind of writing piece this is such as a theoretical argument, an empirical study, a practical explanation, case study, etc. It can be more than one type of writing. Specify what the main objective or thesis. Additionally, determine this piece's intended audience(s).
Ease of Reading: Review the degree to which the authors rely on complex terminology and complicated language and assume what the audience knows. Consider to what degree the overall structure and organization aid understanding.
Evidence: Clarify the types of resources and evidence that are used. How consistent are the authors in drawing upon additional scholarship research to validate claims and how well do they demonstrate the evidence for their findings. Evaluate the reliance on qualitative, quantitative, mixed methods, primary sources, and other types of evidence.
Coherent, clear and strong argument: What the article is trying to communicate is structured in a way that guides the reader thoughtfully through all of its points. Identify if they engage with counterarguments or alternative perspectives.
Clarity of ideas: How straightforward the key points of the article can be deduced including the logical flow of the article, the explicitness of key points, or how well the article summarizes its main ideas.
Reliance on diverse perspectives and research: Consider interdisciplinary approaches, global versus local perspectives, intersectional considerations, historical and contemporary lenses or other types of approaches. The degree to which the research they draw upon represents a variety of standpoints in terms of time of publication, diversity of authorship, publication type, and other relevant factors.
Ability to directly apply ideas into practice: The ease of taking what the article discusses and translating it into teaching, learning, and supporting faculty in developing teaching and learning.
Prompt 2: Reviewing the article
Review the attached document. As an expert educational developer, you must provide a detailed summary of the attached article, focusing on its key points, findings, and recommendations. In particular, highlight how the article's insights and conclusions are applicable to the work of educational developers and faculty.
Each paragraph of your discussion must include specific details and examples from the document.
The first paragraph must discuss any specific strategies, methodologies, or theoretical perspectives presented in the document that can inform or improve teaching and learning practices.
The second paragraph must identify any gaps, challenges, or limitations mentioned in the article that would help educational developers in their work.
Your response must offer significant depth to help educational developers determine the article's relevance and value to their work.
Prompt #3: Interesting Findings
Review the attached document and identify all surprising or unconventional findings or approaches for educational developers or educators?
You must include specific examples and detailed explanations about why they are surprising, unconventional, and/or previously not discussed in the literature on this topic.
Prompt #4: Effective summary
Review the attached document. As an expert educational developer, you must produce the following responses.
The first paragraph must be a comprehensive explanation of the document's main points, ideas, arguments and suggestions.
The second paragraph must be a comprehensive, non-repetitive, condensed explanation of what has been covered throughout this chat.
The third paragraph must include several specific practices, actions, and considerations for an educational developer to integrate into their work based upon the attached document and your summary. For each practice, action, or consideration, you must also include a recommendation for how to implement it.
Every paragraph you generate must include specific and distinct details that are not repeated from previous paragraphs and draw upon examples from the document or extend and apply the ideas to other possibilities.
Prompt #5: Relevant keywords
Provide a bulleted list of 5-8 keywords (no explanations). The keywords should draw from the article, be relevant and beneficial to help educational developers categorize this article.
AI+Edu=Simplified by Lance Eaton is licensed under Attribution-ShareAlike 4.0 International
Good practice, Todd.