Email this article Characterizing University Students’ Geometric Thinking Through Dialogues with Generative Artificial Intelligence in Geometry Transformation Learning
Generative Artificial Intelligence (GenAI) has emerged as a promising technology for supporting mathematical dialogue, feedback, and reasoning in mathematics education. However, research has paid limited attention to how university students’ geometric thinking develops through sustained interaction with GenAI, particularly in geometry transformation learning. This study aims to develop a Dialogic Geometric Thinking Framework that characterizes the dimensions and progression of university students’ geometric thinking during sustained dialogue with ChatGPT. A qualitative exploratory design was employed involving undergraduate mathematics education students enrolled in a Geometry Transformation course at an Indonesian public university. Data were collected from student–ChatGPT dialogue transcripts, students’ written solutions, and reflective interviews. The data were analyzed thematically using reflexive thematic analysis to identify recurring characteristics and relationships among dimensions of geometric thinking and to synthesize them into an integrated framework. The findings identified five interrelated dimensions of geometric thinking: conceptual reasoning, representational coordination, procedural justification, reflective regulation, and mathematical elaboration. These dimensions illustrate how students progressively articulate mathematical concepts, coordinate representations, justify solution procedures, evaluate their reasoning, and extend mathematical ideas during AI-mediated dialogue. The study resulted in a Dialogic Geometric Thinking Framework that provides a process-oriented perspective on the development of university students’ geometric thinking during interaction with GenAI. The framework offers an initial theoretical foundation for understanding and further investigating geometric thinking in AI-mediated mathematics learning.
Keywords: geometric thinking, generative artificial intelligence, chatGPT, geometry transformation, mathematical dialogue.
Akkus-Cikla, O., & Duatepe-Paksu, A. (2010). Students' misconceptions and errors in transformation geometry. International Journal of Mathematical Education in Science and Technology, 41(7), 901–919. https://doi.org/10.1080/0020739X.2010.486451
Albadarin, Y., Saqr, M., Pope, N., et al. (2024). A systematic literature review of empirical research on ChatGPT in education. Discover Education, 3, Article 60. https://doi.org/10.1007/s44217-024-00138-2
Barwell, R. (2023). Sourcing mathematical meaning as a dialogic process: Meaning-focused and language-focused repairs. ZDM–Mathematics Education, 55, 535–550. https://doi.org/10.1007/s11858-023-01467-6
Battista, M. T. (2007). The development of geometric and spatial thinking. In F. K. Lester Jr. (Ed.), Second handbook of research on mathematics teaching and learning (pp. 843–908). Information Age Publishing.
Ben-Dor, N., & Heyd-Metzuyanim, E. (2025). Unifying dialogic learning and mathematics learning: A discursive lens for the study of dialogic mathematics peer learning. Journal of the Learning Sciences, 34(1), 1–34.
Bhullar, P., Joshi, M., & Chugh, R. (2024). ChatGPT in higher education: A synthesis of the literature and a future research agenda. Education and Information Technologies, 29, 21501–21522. https://doi.org/10.1007/s10639-024-12723-x
Braun, V., & Clarke, V. (2022). Thematic analysis: A practical guide. SAGE Publications.
Campbell, J. L., Quincy, C., Osserman, J., & Pedersen, O. K. (2013). Coding in-depth semistructured interviews: Problems of unitization and intercoder reliability and agreement. Sociological Methods & Research, 42(3), 294–320. https://doi.org/10.1177/0049124113500475
Carter, N., Bryant-Lukosius, D., DiCenso, A., Blythe, J., & Neville, A. J. (2014). The use of triangulation in qualitative research. Oncology Nursing Forum, 41(5), 545–547. https://doi.org/10.1188/14.ONF.545-547
Creswell, J. W., & Poth, C. N. (2018). Qualitative inquiry and research design: Choosing among five approaches (4th ed.). SAGE Publications.
Dilling, F., & Herrmann, M. (2024). Using large language models to support pre-service teachers' mathematical reasoning—An exploratory study on ChatGPT as an instrument for creating mathematical proofs in geometry. Frontiers in Artificial Intelligence, 7. https://doi.org/10.3389/frai.2024.1460337
Duval, R. (1999). Representation, vision and visualization: Cognitive functions in mathematical thinking. In F. Hitt & M. Santos (Eds.), Proceedings of the Twenty-First Annual Meeting of the North American Chapter of the International Group for the Psychology of Mathematics Education (Vol. 1, pp. 3–26).
Gulkilik, H., Moyer-Packenham, P. S., Ugurlu, H. H., & Yuruk, N. (2020). Characterizing the growth of one student's mathematical understanding in a multi-representational learning environment. Journal of Mathematical Behavior, 58, 100756. https://doi.org/10.1016/j.jmathb.2020.100756
Jensen, L. X., Buhl, A., Sharma, A., Bearman, M., & colleagues. (2025). Generative AI and higher education: A review of claims from the first months of ChatGPT. Higher Education, 89, 1145–1161. https://doi.org/10.1007/s10734-024-01265-3
Kallio, H., Pietilä, A.-M., Johnson, M., & Kangasniemi, M. (2016). Systematic methodological review: Developing a framework for a qualitative semi-structured interview guide. Journal of Advanced Nursing, 72(12), 2954–2965. https://doi.org/10.1111/jan.13031
Khatin-Zadeh, O., Farsani, D., & Breda, A. (2023). How can transforming representation of mathematical entities help us employ more cognitive resources? Frontiers in Psychology, 14, 1091678. https://doi.org/10.3389/fpsyg.2023.1091678
Lavicza, Z., Abar, C. A. A. P., & Tejera, M. (2023). Spatial geometric thinking and its articulation with the visualization and manipulation of objects in 3D. Educação Matemática Pesquisa, 25(2), 258–277. https://doi.org/10.23925/1983-3156.2023v25i2p258-277
Lincoln, Y. S., & Guba, E. G. (1985). Naturalistic inquiry. SAGE Publications.
Maifa, T. S., Suryadi, D., & Fatimah, S. (2025). Identifying learning obstacles in proof construction for geometric transformations: Conceptual, procedural, and visualization errors. Infinity Journal, 14(3), 673–694. https://doi.org/10.22460/infinity.v14i3.p673-694
Mercer, N. (2000). Words and minds: How we use language to think together. Routledge.
Merriam, S. B., & Tisdell, E. J. (2016). Qualitative research: A guide to design and implementation (4th ed.). Jossey-Bass.
Moschkovich, J. N. (2015). Academic literacy in mathematics for English learners. The Journal of Mathematical Behavior, 40, 43–62. https://doi.org/10.1016/j.jmathb.2015.01.005
Pardos, Z. A., & Bhandari, S. (2024). ChatGPT-generated help produces learning gains equivalent to human tutor-authored help on mathematics skills. PLOS ONE, 19(5), e0304013. https://doi.org/10.1371/journal.pone.0304013
Schindler, M., Lilienthal, A. J., Müller, T., & colleagues. (2024). Students' use of generative artificial intelligence for proving mathematical statements. ZDM–Mathematics Education, 56, 1531–1551.
Trimurtini, T., Waluya, S. B., Sukestiyarno, Y. L., & Kharisudin, I. (2022). A systematic review on geometric thinking: A review research between 2017–2021. European Journal of Educational Research, 11(3), 1535–1552. https://doi.org/10.12973/eu-jer.11.3.1535
Usiskin, Z. (1982). Van Hiele levels and achievement in secondary school geometry: Final report of the Cognitive Development and Achievement in Secondary School Geometry (CDASSG) Project. University of Chicago, Department of Education.
Walkington, C. (2026). The implications of generative artificial intelligence for mathematics education. School Science and Mathematics, 126(4), 356–365.
Wegerif, R. (2007). Dialogic education and technology: Expanding the space of learning. Boston, MA: Springer US.
Yusuf, N. M. N., Mohamed, M., Asari, S., & Abdullah, A. H. (2024). Generative AI in education and research: A systematic mapping review. Review of Education, 12(3), e3489. https://doi.org/10.1002/rev3.3489
Zbiek, R. M., Heid, M. K., Blume, G. W., & Dick, T. P. (2007). Research on technology in mathematics education: A perspective of constructs. In F. K. Lester Jr. (Ed.), Second handbook of research on mathematics teaching and learning (pp. 1169–1207). Information Age Publishing.
Zhang, X., Zhang, P., Shen, Y., Liu, M., Wang, Q., Gašević, D., & Fan, Y. (2024). A systematic literature review of empirical research on applying generative artificial intelligence in education. Frontiers of Digital Education, 1(3), 223–245. https://doi.org/10.1007/s44366-024-0028-5
Refbacks
- There are currently no refbacks.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
View My Stats