ChatGPT in Physics Education: A Systematic Literature Review and Bibliometric Mapping of Pedagogical Roles, Challenges, and Implications
DOI:
https://doi.org/10.23960/jpf.v14i1.29Keywords:
ChatGPT, physics education, artificial intelligence in education, large language modelAbstract
The rapid advancement of Artificial Intelligence (AI), particularly Large Language Models (LLMs) such as ChatGPT, has accelerated its integration into education. However, evidence regarding its pedagogical value and limitations in physics education remains fragmented, especially concerning conceptual accuracy, discipline-specific hallucination risks, and teacher roles in AI-supported learning. This study provides a physics-specific synthesis of ChatGPT implementation in physics education by examining its contributions to conceptual learning, assessment, instructional design, and teacher development. A Systematic Literature Review (SLR) following the PRISMA protocol was conducted using the Scopus database in the Physics and Astronomy subject category. The search employed the keywords "ChatGPT", "Artificial Intelligence", and "Physics Education", yielding 35 records. Following screening and eligibility assessment, 15 studies were retained for bibliometric mapping, while seven core studies directly investigating ChatGPT implementation in physics learning were selected for qualitative synthesis. Bibliometric analysis using VOS-viewer identified three thematic clusters, AI capabilities, physics implementation, and pedagogical integration. The findings indicate that ChatGPT supports conceptual discussions, experimental data analysis, lesson plan development, and teacher pedagogical training. Automated assessment accuracy reached approximately 70% after domain-specific fine-tuning, whereas conceptual inaccuracies remained evident, with reported error rates ranging from 15% to 25% in precision physics contexts. The review demonstrates that ChatGPT should not function as an autonomous physics tutor but should be embedded within teacher-validated instructional designs that explicitly evaluate conceptual accuracy, reasoning transparency, and student verification processes in physics learning.
References
Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., & Askell, A. (2020). Language models are few-shot learners. 34th Conference on Neural Information Processing Systems (NeurIPS 2020), 33, 1877–1901. https://doi.org/10.48550/arXiv.2005.14165
Elson, L., Gaughan, L., Hopton, B., Lloyd-Brown, S., Briggs, C., Gharamti, M., & Moriarty, P. (2025). ‘ChatGPT did my homework’: lessons learnt from embedding a chatbot in undergraduate coursework. Physics Education, 60(2). https://doi.org/10.1088/1361-6552/adb363
Gregorcic, B., & Pendrill, A.-M. (2023). ChatGPT and the frustrated Socrates. Physics Education, 58(3). https://doi.org/10.1088/1361-6552/acc299
Gregorcic, B., Polverini, D., & Sarlah, M. (2024). ChatGPT as a tool for honing teachers’ Socratic dialogue skills. Physics Education, 59(045005). https://doi.org/10.1088/1361-6552/ad3d21
Hasan, N., Polin, J. A., Ahmmed, M. R., Sakib, M. M., Jahin, M. F., & Rahman, M. M. (2024). A novel approach to analyzing the impact of AI, ChatGPT, and chatbot on education using machine learning algorithms. Bulletin of Electrical Engineering and Informatics, 13(4), 2951–2958. https://doi.org/10.11591/eei.v13i4.7158
Jang, M., Kahng, Y. H., Lee, S. D., Lim, O. Y., & Park, C. J. (2024). Case study of high school physics class development utilizing ChatGPT. New Physics: Sae Mulli, 74, 779–787. https://doi.org/10.3938/NPSM.74.779
LeeJ. (2025). Research on automated scoring for short constructed-response questions through fine-tuning ChatGPT. New Physics: Sae Mulli, 75, 381–393. https://doi.org/10.3938/NPSM.75.381
Luckin, R., Holmes, W., Griffiths, M., & Forcier, L. B. (2016). Intelligence unleashed: An argument for AI in education. In London: Pearson. Pearson. https://static.googleusercontent.com/media/edu.google.com/en//pdfs/Intelligence-Unleashed-Publication.pdf
Park, H. K., & Park, J. (2024). Lesson plan development for pre-service elementary school teachers through collaboration with AI: Focused on ChatGPT. New Physics: Sae Mulli, 74, 215–226. https://doi.org/10.3938/NPSM.74.215
Polverini, D., & Gregorcic, B. (2024). How understanding large language models can inform the use of ChatGPT in physics education. European Journal of Physics, 45(2). https://doi.org/10.1088/1361-6404/ad1420
Rahman, M. M., & Watanobe, Y. (2023). ChatGPT for education and research: Opportunities, threats, and strategies. Applied Sciences, 13(9), 5783. https://doi.org/10.3390/app13095783
Redish, E. F. (2003). Teaching physics with the physics suite. In Hoboken, NJ : John Wiley & Son. John Wiley & Sons. https://www.academia.edu/112737022/Teaching_Physics_with_the_Physics_Suite
Russell, S., & Norvig, P. (2021). Artificial Intelligence: A modern approach. Pearson Education. http://lib.ysu.am/disciplines_bk/efdd4d1d4c2087fe1cbe03d9ced67f34.pdf
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Dhita Thivani Linch Hutabarat, Sintia Sintia, Heru Kuswanto
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
