- Physical Review Journals
All JournalsPhysics Magazine

Physical Review Physics Education Research

Reuse & Permissions

It is not necessary to obtain permission to reuse this article or its components as it is available under the terms of the Creative Commons Attribution 4.0 International license. This license permits unrestricted use, distribution, and reproduction in any medium, provided attribution to the author(s) and the published article's title, journal citation, and DOI are maintained. Please note that some figures may have been included with permission from other third parties. It is your responsibility to obtain the proper permission from the rights holder directly for these figures.

Export citation

Export citation

Choose format for download:

Download Citation
  • Open Access

DeepSeek-assisted physics instructional design: An empirical study of high school physics teaching

Dazhen Tong1, Huihui Wu2, A. Y. M. Atiquil Islam3,4,*, Junci Liu2, Lei Jiang5, and Hongmei Ren2,†

  • *Contact author: prof.atiqul@gmail.com
  • †Contact author: hmren@ahnu.edu.cn
PDF

Phys. Rev. Phys. Educ. Res. 22, 010151 – Published 30 June, 2026

DOI: https://doi.org/10.1103/bxql-gzfk

Abstract

Generative artificial intelligence (GenAI) has shown growing potential in supporting teacher education, yet little is known about how preservice teachers collaborate with AI during instructional design (ID). This study examined the effects of DeepSeek, a Chinese large language model, on preservice physics teachers’ ID performance and cognitive processes. A quasiexperimental design was conducted with 220 participants completing a 45-min ID on Newton’s third law, either with or without DeepSeek assistance. Data from IDs, interaction logs, and interviews were analyzed through statistical tests, epistemic network analysis (ENA), and thematic coding. Results indicated that the DeepSeek-assisted group outperformed the control group in analytical and structural aspects of ID, such as teaching content analysis and learner analysis. ENA revealed that high-performing participants exhibited proactive “problem representation–AI interaction–monitoring” patterns, while low-performing participants relied on reactive prompting. Interviews further confirmed that AI was helpful in contextual introductions and experiment design but also revealed issues such as outdated curriculum references and overly absolute expressions that lacked sensitivity to teaching contexts. The findings suggest that GenAI can serve as a cognitive scaffold when used strategically and highlight the need to integrate AI literacy and metacognitive training into teacher education.

View figure in article

Physics Subject Headings (PhySH)

Article Text

Supplemental Material

References (42)

  1. M. G. de Souza, M. Won, D. Treagust, and A. Serrano, Visualising relativity: Assessing high school students’ understanding of complex physics concepts through AI-generated images, Phys. Educ. 59, 025018 (2024).
  2. Y. Ben-Zion, R. E. Zarzecki, J. Glazer, and N. D. Finkelstein, Leveraging AI for rapid generation of physics simulations in education: Building your own virtual lab, Phys. Teach. 63, 424 (2025).
  3. E. Kasneci, S. Krebs, C. Spohn, F. Dorgerloh, A.-S. Mestres, and C. Schulz, ChatGPT for good? On opportunities and challenges of large language models for education, Learn. Individ. Differ. 103, 102274 (2023).
  4. M. I. Baig and E. Yadegaridehkordi, ChatGPT in the higher education: A systematic literature review and research challenges, Int. J. Educ. Res. 127, 102411 (2024).
  5. J. Kim, S.-S. Lee, R. Detrick, J. Wang, and N. Li, Students-Generative AI interaction patterns and its impact on academic writing, J. Comput. Higher Educ. 38, 504 (2025).
  6. J. Kim, Y. Ham, and S.-S. Lee, Differences in student-AI interaction process on a drawing task: Focusing on students’ attitude towards AI and the level of drawing skills, Aust. J. Educ. Technol. 40, 19 (2024).
  7. D. Tong, B. Jin, Y. Tao, H. Ren, A. Y. M. Atiquil Islam, and L. Bao, Exploring the role of human-AI collaboration in solving scientific problems, Phys. Rev. Phys. Educ. Res. 21, 010149 (2025).
  8. S. Halawa, T. C. Lin, and Y. S. Hsu, Exploring instructional design in K-12 STEM education: A systematic literature review, Int. J. STEM Educ. 11, 43 (2024).
  9. D. Schiering, S. Sorge, M. M. Keller, and K. Neumann, A proficiency model for pre-service physics teachers’ pedagogical content knowledge (PCK)—What constitutes high-level PCK?, J. Res. Sci. Teach. 60, 136 (2023).
  10. C. Kulgemeyer, A. Borowski, D. Buschhüter, P. Enkrott, M. Kempin, P. Reinhold, and C. Vogelsang, Professional knowledge affects action-related skills: The development of preservice physics teachers’ explaining skills during a field experience, J. Res. Sci. Teach. 57, 1554 (2020).
  11. G. Resbiantoro, R. Setiani, and Dwikoranto, A review of misconception in physics: The diagnosis, causes, and remediation, J. Turk. Sci. Educ. 19, 403 (2022), https://mail.tused.org/index.php/tused/article/view/924.
  12. S. Soeharto and B. Csapó, Evaluating item difficulty patterns for assessing student misconceptions in science across physics, chemistry, and biology concepts, Heliyon 7, e08352 (2021).
  13. W. Dick, A history of instructional design and its impact on educational psychology, in Historical Foundations of Educational Psychology (Plenum Press, Boston, 1987), p. 183.
  14. R. A. Reiser and J. V. Dempsey, Trends and Issues in Instructional Design, 2nd ed. (Pearson Education, Upper Saddle River, NJ, 2007), p. 11.
  15. L. S. Shulman, Those who understand: Knowledge growth in teaching, Educ. Res. 15, 4 (1986).
  16. W. S. Yu, From “basic knowledge and skills” to three-dimensional goals to core literacy: Three stages of curriculum and teaching reform in China over 40 years of reform and opening up, Curric. Teach. Mater. Method 39, 40 (2019).
  17. Y. Y. Guo, From three-dimensional curriculum objectives to core literacy in physics, Phys. Teach. 39, 2 (2017), https://kns.cnki.net/kcms2/article/abstract?v=wGRGwcz8A0e7yGb-5Qypp4S1quHM6cxBUyoJ1hUGNwjau5UwokltOu4zCNrI_yhPs71dKc6n9RqAqK313-hk_2SU7MrpDQ0VjC7OzL3wx6Gw4Q-6FtBSGbs0em9ppzTqFWuZU9YDvUG2kO91lToMMiwwL8a3EMUJ0AVxhngudMAtfwUra3Jqtw==&uniplatform=NZKPT&language=CH.
  18. N. Li, J. Zhang, and Z. Tang, Analysis and implications of the current situation of middle school physics teaching design from the perspective of core literacy: Based on an analysis of physics teacher articles from 2016 to 2020, Phys. Teach. 42, 63 (2021), https://kns.cnki.net/kcms2/article/abstract?v=wGRGwcz8A0cvwhnr2JUPj--i_lrgIqC5Jar6lXABZ6AQr5LKF_bK7ugGoSmzNLc1yvUDAraaUFaQlexJO_msYt2o6D9A1MEeFrtGkIpZ7W1Rvm9Z7Wbybu-DQy6l2ubJ5RWm3ALinTtyeEr4Uw2rvfIl5tdGVp3-BKcBWv7HybkrAKf5Ak6RUQ==&uniplatform=NZKPT&language=CHS.
  19. S. Kapon and A. Merzel, Content-specific pedagogical knowledge, practices, and beliefs underlying the design of physics lessons: A case study, Phys. Rev. Phys. Educ. Res. 15, 010125 (2019).
  20. S. Küchemann, S. Steinert, N. Revenga, M. Schweinberger, Y. Dinc, K. E. Avila, and J. Kuhn, Can ChatGPT support prospective teachers in physics task development?, Phys. Rev. Phys. Educ. Res. 19, 020128 (2023).
  21. G. Kortemeyer, J. Nöhl, and D. Onishchuk, Grading assistance for a handwritten thermodynamics exam using artificial intelligence: An exploratory study, Phys. Rev. Phys. Educ. Res. 20, 020144 (2024).
  22. T. Wang and Z. Chen, Exploring generative AI assisted feedback writing for students’ written responses to a physics conceptual question with prompt engineering and few-shot learning, Phys. Rev. Phys. Educ. Res. 20, 010152 (2024).
  23. G. Kortemeyer, Toward AI grading of student problem solutions in introductory physics: A feasibility study, Phys. Rev. Phys. Educ. Res. 19, 020163 (2023).
  24. K. E. Avila, S. Steinert, S. Ruzika, J. Kuhn, and S. Küchemann, Using ChatGPT for teaching physics, Phys. Teach. 62, 536 (2024).
  25. D. T. T. Mai, C. V. Da, and N. V. Hanh, The use of ChatGPT in teaching and learning: A systematic review through SWOT analysis approach, Front. Educ. 9, 1328769 (2024).
  26. P. Tschisgale, P. Wulff, and M. Kubsch, Integrating artificial intelligence-based methods into qualitative research in physics education research: A case for computational grounded theory, Phys. Rev. Phys. Educ. Res. 19, 020123 (2023).
  27. T. Jiang, Z. Sun, S. Fu, and Y. Lv, Human-AI interaction research agenda: A user-centered perspective, Data Inf. Manage. 8, 100078 (2024).
  28. J. Kim, S. Yu, S. S. Lee, and R. Detrick, Students’ prompt patterns and its effects in AI-assisted academic writing: Focusing on students’ level of AI literacy, J. Res. Technol. Educ. 58, 638 (2025).
  29. A. R. Malik, Y. Pratiwi, K. Andajani, I. W. Numertayasa, S. Suharti, A. Darwis, and Marzuki, Exploring artificial intelligence in academic essay: Higher education students perspective, Int. J. Educ. Res. Open. 5, 100296 (2023).
  30. A. Nguyen, Y. Hong, B. Dang, and X. Huang Human-AI collaboration patterns in AI-assisted academic writing, Stud. Higher Educ. 49, 847 (2024).
  31. C. Zhai, S. Wibowo, and L. D. Li, The effects of over-reliance on AI dialogue systems on students’ cognitive abilities: A systematic review, Smart Learn. Environ. 11, 28 (2024).
  32. G. G. Lee and X. Zhai, Using ChatGPT for science learning: A study on pre-service teachers’ lesson planning, IEEE Trans. Learn. Technol. 17, 1643 (2024).
  33. W. Dick, L. Carey, and J. O. Carey, The Systematic Design of Instruction, 7th ed. (Pearson, Upper Saddle river, NJ, 2008).
  34. See Supplemental Material at https://link.aps.org/supplemental/10.1103/bxql-gzfk for details.
  35. V. Braun and V. Clarke, Using thematic analysis in psychology, Qual. Res. Psychol. 3, 77 (2006).
  36. T. K. Koo and M. Y. Li, A guideline of selecting and reporting intraclass correlation coefficients for reliability research, J. Chiropr. Med. 15, 155 (2016).
  37. J. Cohen, Statistical Power Analysis for the Behavioral Sciences, 2nd ed. (Lawrence Erlbaum Associates, Hillsdale, NJ, 1988).
  38. J. T. E. Richardson, Eta squared and partial eta squared as measures of effect size in educational research, Educ. Res. Rev. 6, 135 (2011).
  39. S. Zha, Y. Qiao, Q. Hu, Z. Li, J. Gong, and Y. Xu, Designing child-centric AI learning environments: Insights from LLM-enhanced creative project-based learning, arXiv:2403.16159.
  40. G. Franceschelli and M. Musolesi, On the creativity of large language models, AI Soc. 40, 3785 (2025).
  41. E. F. Risko and S. J. Gilbert, Cognitive offloading, Trends Cogn. Sci. 20, 676 (2016).
  42. S. J. Gilbert, Strategic offloading of delayed intentions into the external environment, Q. J. Exp. Psychol. 68, 971 (2015).

Outline

Information

Phys. Rev. Phys. Educ. Res. 22, 010151– Published 30 June, 2026
  • Received 10 December 2025
  • Accepted 27 May 2026
Crossmark - Check for updates button
Creative Commons Logo

Published by the American Physical Society under the terms of the Creative Commons Attribution 4.0 International license. Further distribution of this work must maintain attribution to the author(s) and the published article’s title, journal citation, and DOI.

Published by the American Physical Society

Sign In to Your Journals Account

Filter

Filter

Article Lookup

Enter a citation