Author:
Riabko Andrii V.,Vakaliuk Tetiana A.
Abstract
This study investigates the efficacy of large language model (LLM)-powered chatbots in guiding physics problem-solving, examining whether they can effectively supplement teacher-led learning. A customised chatbot was developed leveraging ChatGPT to provide step-by-step assistance through a structured problem-solving algorithm. Its impact was evaluated via an experimental study with 12th-grade physics students (N = 24) randomly assigned to a teacher-guided or chatbot-guided group for problem-solving practice. A Mann-Whitney U test revealed no significant differences in problem-solving competency between conditions. Qualitative analysis of conversational logs indicates the chatbot successfully emulated key teacher scaffolding behaviours. Our findings suggest AI tutors can deliver personalised, interactive support akin to human teachers, offering viable supplements to augment physics learning. Further research should explore optimising LLM training, human-chatbot balances, and impacts across diverse educational settings.
Publisher
Academy of Cognitive and Natural Sciences
Reference26 articles.
1. Ausat, A.M.A., Massang, B., Efendi, M., Nofirman, N. and Riady, Y., 2023. Can Chat GPT Replace the Role of the Teacher in the Classroom: A Fundamental Analysis. Journal on Education, 5(4), pp.16100–16106. Available from: https://jonedu.org/index.php/joe/article/view/2745.
2. Barbas, M.P., Vieira, A.T. and Branco, P.D., 2024. The Importance of Chat GPT Training for Higher Education: Case Study. In: N. Martins and D. Brandão, eds. Advances in Design and Digital Communication IV. Cham: Springer Nature Switzerland, Springer Series in Design and Innovation, vol. 35, pp.695–705. Available from: https://doi.org/10.1007/978-3-031-47281-7_57.
3. Bitzenbauer, P., 2023. ChatGPT in physics education: A pilot study on easy-to-implement activities. Contemporary Educational Technology, 15(3), p.ep430. Available from: https://doi.org/10.30935/cedtech/13176.
4. Budzianowski, P., Ultes, S., Su, P.H., Mrkšić, N., Wen, T.H., Casanueva, I., Rojas-Barahona, L.M. and Gašić, M., 2017. Sub-domain Modelling for Dialogue Management with Hierarchical Reinforcement Learning. In: K. Jokinen, M. Stede, D. DeVault and A. Louis, eds. Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue. Saarbrücken, Germany: Association for Computational Linguistics, pp.86–92. Available from: https://doi.org/10.18653/v1/W17-5512.
5. Chi, M.T.H., 2005. Commonsense Conceptions of Emergent Processes: Why Some Misconceptions Are Robust. The Journal of the Learning Sciences, 14(2), pp.161–199. Available from: https://www.public.asu.edu/~mtchi/papers/EmergJLSpdf.pdf.
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献