과학교육 전문가의 ChatGPT를 활용한 문제해결 과정의 상호작용 분석
Analysis of Interactions in Problem-Solving Processes Using ChatGPT by Science Education Experts
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
This study analyzed the interaction types exhibited by science education experts while utilizing generative AI, ChatGPT-4, to solve tasks, and explored the characteristics of human-AI interactions based on these findings. The research employed grounded theory methodology to examine interaction data generated during the development of conceptual frameworks for socio-scientific issue learning. Through analyzing the progression of interactions, key features were identified. The findings revealed eight distinct interaction types: Simple Information Request, Simple Task Instruction, Judgment and Selection Request, Product Revision Request, Application and Example Request, Iterative Refinement Request, Insightful Thinking Question, and Context-Driven Task Instruction. Among these, Iterative Refinement Requests and Application and Example Requests were the most frequently used. The study further observed that experts engaged in repetitive and cyclical processes to refine and enhance the outputs generated by the AI. This research highlights the potential of AI as a collaborative partner, transcending its role as a mere information provider. These findings offer a theoretical foundation for refining and systematically utilizing human-AI interactions and are expected to contribute to the development of effective collaboration strategies between humans and AI for more efficient and meaningful outcomes.
Abstract
This study analyzed the interaction types exhibited by science education experts while utilizing generative AI, ChatGPT-4, to solve tasks, and explored the characteristics of human-AI interactions based on these findings. The research employed grounded theory methodology to examine interaction data generated during the development of conceptual frameworks for socio-scientific issue learning. Through analyzing the progression of interactions, key features were identified. The findings revealed eight distinct interaction types: Simple Information Request, Simple Task Instruction, Judgment and Selection Request, Product Revision Request, Application and Example Request, Iterative Refinement Request, Insightful Thinking Question, and Context-Driven Task Instruction. Among these, Iterative Refinement Requests and Application and Example Requests were the most frequently used. The study further observed that experts engaged in repetitive and cyclical processes to refine and enhance the outputs generated by the AI. This research highlights the potential of AI as a collaborative partner, transcending its role as a mere information provider. These findings offer a theoretical foundation for refining and systematically utilizing human-AI interactions and are expected to contribute to the development of effective collaboration strategies between humans and AI for more efficient and meaningful outcomes.
참고문헌 (37)
- 김준동, "프롬프트 엔지니어링(Prompt Engineering)을 활용한 ‘진료수행시험 연습용 챗 봇(CPX Practicing Chatbot)’ 시범 개발", 대한한의학회지, 45(1), pp.203~214 (2024)
- 민태호, "프롬프트에 따른 GPT 언어 모델의물리 서술형 문항 채점 결과 비교", New Physics : SaeMulli, 74(5), pp.504~551 (2024)
- 송혜빈, "인간-AI 협력 역량 향상을 위한 활동중심수업 설계원리 개발", 박사, pp.2023
- 이윤빈, "대학생 필자의 글쓰기 과정에서 챗GPT에 대한 질문 양상 연구 : 쓰기 수준별 필자 집단의 비교를 중심으로", 교양 교육 연구, 8(17), pp.49~66 (2023)
- 최숙영, "AI 리터러시 프레임워크에 대한 연구", 컴퓨터교육학회 논문지, 25(5), pp.73~84 (2022)
- 한진영, "문제중심학습과 챗GPT : 프롬프트와문제해결력에 대한 탐색", 교양학연구, 26(1), pp.111~118 (2024)
- 허동석, "프롬프트 개발을 통한 수능 국어 맞춤형 문제 생성 시스템 제안", HCI Korea2024 Conference Proceedings, pp.183~192 (2024)
- Anderson, L. W., "A Taxonomy for Learning, Teaching, and Assessing: A Revision of Bloom's Taxonomy of Educational Objectives: Complete Edition" (2001), Addison Wesley Longman, Inc.
- Bickmore, T., "Relational agents: A model and implementation of building user trust", Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, pp.396~403 (2001)
- Brown, T. B., "Language models are few-shot learners", Advances in Neural Information Processing Systems, 33, pp.1877~1901 (2020)
- Bulat, A., "Language-aware soft prompting : Text-to-text optimization for few-and zero-shot adaptation of V & L Models", International Journal of Computer Vision, 132(4), pp.1108~1125 (2024)
- Chang, C. J., "An analysis of student collaborative problem solving activities mediated by collaborative simulations", Computers & Education, 114, pp.222~235 (2017)
- Cooper G., "Examining science education in ChatGPT : An exploratory study of generative artificial intelligence", Journal of Science Education and Technology, 32(3), pp.444~452 (2023)
- Dai, Y., "Collaborative construction of artificial intelligence curriculum in primary schools", Journal of Engineering Education, 112(1), pp.23~42 (2023)
- Endsley, M. R., "Toward a theory of situation awareness in dynamic systems", Human factors, 37(1), pp.32~64 (1995)
- Guo, Y., "Leveraging chatgpt for enhancing critical thinking skills", Journal of Chemical Education, 100(12), pp.4876~4883 (2023)
- Hogan, K., "Discourse patterns and collaborative scientific reasoning in peer and teacher-guided discussions", Cognition and Instruction, 17(4), pp.379~432 (1999)
- Imran, M., "Analyzing the role of ChatGPT as a writing assistant at higher education level: A systematic review of the literature", Contemporary Educational Technology, 15(4), pp.ep464~ (2023)
- "What is Human-Computer Interaction (HCI)?" (2016)[URL]
- "What is Human-AI Interaction (HAX)?" (2023)[URL]
- Kim, M., "Adapting to the future : ChatGPT as a means for supporting constructivist learning environments", TechTrends, 68, pp.37~46 (2023)
- Korinek, A., "Generative AI for economic research : Use cases and implications for economists", Journal of Economic Literature, 61(4), pp.1281~1317 (2023)
- Li, B., "Reconceptualizing self-directed learning in the era of generative AI : An exploratory analysis of language learning", IEEE Transactions on Learning Technologies, 17, pp.1515~1529 (2024)
- Norman, D., "Cognitive engineering. User Centered System Design" (1986), Lawrence Erlbaum Associates, Inc
- Parasuraman, R., "Humans and automation : Use, misuse, disuse, abuse", Human Factors, 39(2), pp.230~253 (1997)
- Patel, V. L., "The coming of age of artificial intelligence in medicine", Artificial Intelligence in Medicine, 46(1), pp.5~17 (2009)
- Rasul, T., "The role of ChatGPT in higher education : Benefits, challenges, and future research directions", Journal of Applied Learning and Teaching, 6(1), pp.41~56 (2023)
- Robertson, J., "Game Changers: A Generative AI Prompt Protocol to Enhance Human-AI Knowledge Co-Construction" (2024), Business Horizons
- Rummel, N., "Learning to collaborate : An instructional approach to promoting collaborative problem solving in computer-mediated settings", The Journal of the Learning Sciences, 14(2), pp.201~241 (2005)
- Shen, Y., "HuggingGPT : Solving AI tasks with ChatGPT and its friends in hugging face", Advances in Neural Information Processing Systems, 36 (2024)
- Shneiderman, B., "Bridging the gap between ethics and practice : Guidelines for reliable, safe, and trustworthy human-centered AI systems", ACM Transactions on Interactive Intelligent Systems(TiiS), 10(4), pp.1~31 (2020)
- Smith, A., "Old dog, new tricks? Exploring the potential functionalities of ChatGPT in supporting educational methods in social psychiatry", International Journal of Social Psychiatry, 69(8), pp.1882~1889 (2023)
- Strauss, A., "Basics of Qualitative Research Techniques" (1998)
- Sundberg, L., "Democratizing artificial intelligence : How no-code AI can leverage machine learning operations", Business Horizons, 66(6), pp.777~788 (2023)
- Wei J., "Chain-of-thought prompting elicits reasoning in large language models", Advances in Neural Information Processing Systems, 35, pp.24824~24837 (2022)