MoPI.IA: exploring the usefulness of generative AI for thesis project ideation
DOI:
https://doi.org/10.31637/epsir-2024-804Keywords:
academic research, chatbot, ChatGPT, generative artificial intelligence, prompt engineering, research proposal, research topic ideation, thesisAbstract
Introduction: The “Modelo Personal para la Investigación” (MoPI) is a methodological tool created at the Pontificia Universidad Católica del Perú (PUCP) to support students in the elaboration of thesis proposals. In 2023, the MoPI.IA project was launched to integrate generative AI (IAG) into the MoPI methodology, with the aim of improving the ideation of research topics. Methodology: In this first phase of the project, ChatGPT 3.5 was used applying prompts engineering techniques. The responses generated by the chatbot were evaluated for relevance, consistency and practical value. Results: Initial exploration showed that MoPI.IA has significant benefits, especially for students facing difficulties in generating thesis ideas. The incorporation of chatbots showed great potential in this process. Discussion:
Although MoPI.IA proved useful in research topic ideation, areas for improvement were identified in prompt engineering techniques and chatbot selection. Conclusions: Future research will evaluate other chatbots and additional techniques to further improve the MoPI methodology, with the goal of further innovation in supporting students in formulating thesis projects.
Downloads
References
6. Referencias
Abreu, J. L. (2015). Síndrome Todo Menos Tesis (TMT). Daena: International Journal of Good Conscience, 10(2), 246-259. https://bit.ly/3W8zzKH
Anthropic. (s.f.). Ingeniería de prompts. https://bit.ly/AnthropicIngenieriaPrompts
Ben-Zur, L. (2024, 2 de enero). Beyond the Prompt: Why Rigid AI Frameworks Stifle True Conversational Potential. LBZ Advisory. https://bit.ly/3W7KHre
Casado, E. (2019). The Personal Model for Research version 2 and its visualization method to learn design of research proposals. Education for Information, 35(3), 319-335. https://doi.org/10.3233/EFI-190283 DOI: https://doi.org/10.3233/EFI-190283
DAIR.AI. (s.f.). Prompt Engineering Guide. https://www.promptingguide.ai/
Jacks, P., Chubin, D. E., Porter, A. L. y Connolly, T. (1983). The ABCs of ABDs: A Study of Incomplete Doctorates. Improving College and University Teaching, 31(2), 74-81. https://doi.org/10.1080/00193089.1983.10533805 DOI: https://doi.org/10.1080/00193089.1983.10533805
Kaplan, J. (2024). Generative artificial intelligence: What everyone needs to know. Oxford University Press.
Khan, I. (2024). The quick guide to prompt engineering. Wiley.
Mahdawi, A. (2024, 12 de enero). What is going on with ChatGPT? The Guardian. https://bit.ly/46880pa
Merriam-Webster. (s.f.). generative AI. En Merriam-Webster Dictionary. https://bit.ly/3W5wzPh
Mizrahi, G. (2024). Unlocking the Secrets of Prompt Engineering. Packt Publishing Ltd.
Musiol, M. (2024). Generative AI: Navigating the course to the artificial general intelligence future (1ª ed.). John Wiley and Sons.
Mustafa, N. (2024, 7 de febrero). Mastering ChatGPT: Boost Your Creativity with Expert Prompt Engineering Techniques. Medium. https://bit.ly/MustafaMasteringChatGPT
OpenAI. (s.f.). Prompt engineering. https://bit.ly/OpenAIPromptEngineering
Ryan, R. M. y Deci, E. L. (2000). Intrinsic and extrinsic motivations: Classic definitions and new directions. Contemporary Educational Psychology, 25(1), 54-67. https://doi.org/10.1006/ceps.1999.1020 DOI: https://doi.org/10.1006/ceps.1999.1020
Altman, S. [@sama]. (2022, 30 de noviembre). Today we launched ChatGPT. Try talking with it here. [Tweet]. https://x.com/sama/status/1598038815599661056
Sherry, B. (2023, 12 de diciembre). ChatGPT is showing signs of laziness. OpenAI dice que la IA podría necesitar una solución. Inc.com. https://www.inc.com/ben-sherry/chatgpt-is-showing-signs-of-laziness-openai-says-ai-might-need-a-fix.html
The Prompt Index. (s.f.). https://www.thepromptindex.com/index.php
Wolfe, C. R. (2024, 29 de abril). Modern advances in prompt engineering [Boletín de Substack]. Deep (Learning) Focus. https://bit.ly/WolfeModernAdvancesPromptEngineering
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Edilberto Casado Márquez
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Authors who publish with this journal agree to the following terms:- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Non Commercial, No Derivatives Attribution 4.0. International (CC BY-NC-ND 4.0.), that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
