Generative artificial intelligence (AI) tools such as ChatGPT are increasingly used by students to obtain explanations and solutions to mathematics problems. However, access to answers does not necessarily mean that students examine the underlying reasoning. This study aimed to describe students’ interaction patterns with ChatGPT when solving image-based mathematics problems, variations in these patterns across two problems, and how students responded to, sought clarification of, or challenged ChatGPT-generated solutions. A qualitative descriptive design was employed. The participants were Grade 9 students of one intact class (total sampling), and the records of 31 students who worked on two image-based problems, concerning the area of a trapezoidal footpath and the painted area of a photo frame, were analyzed. The primary data consisted of student–ChatGPT conversation transcripts exported from shared conversation links. The transcripts were analyzed descriptively and qualitatively using six predefined interaction patterns: requesting a solution and then ending the interaction; seeking clarification; requesting a re-explanation; checking an answer or testing a method; following a solution step by step; and connecting or redirecting the interaction. The unit of analysis was the student–problem episode, and overlapping codes were permitted. The findings indicate that students did more than request answers. Some asked for the rationale behind a solution step, proposed strategies for confirmation, requested further explanations, responded to practice questions posed by ChatGPT, and made connections between the two problems. Two students questioned the complexity or necessity of ChatGPT’s chosen method. Differences between the problems were primarily reflected in the content of students’ questions. These findings are descriptive and are not intended to establish the prevalence of interaction patterns, learning outcomes, or causal relationships. The findings suggest a need for task design and teacher guidance that encourage students to verify and evaluate AI-generated solutions.
Downloads
- Braskén, M., Berts, K.-E., Wallin, S., & Frilund, S. (2025). Students’ use of ChatGPT in an algebra class: A case study of prompts and attitudes. LUMAT, 13(1), Art. 16. https://doi.org/10.31129/LUMAT.13.1.2877
- Bulut, N., & Borromeo Ferri, R. (2026). AI-powered learning: Exploring secondary school students’ use of ChatGPT for solving mathematical modelling problems. ZDM – Mathematics Education, 58, 993–1009. https://doi.org/10.1007/s11858-026-01803-6
- Dao, X.-Q., & Le, N.-B. (2023). Investigating the effectiveness of ChatGPT in mathematical reasoning and problem solving: Evidence from the Vietnamese National High School Graduation Examination [Preprint]. arXiv. https://doi.org/10.48550/arXiv.2306.06331
- Feng, S. (2025). Group interaction patterns in generative AI-supported collaborative problem solving: Network analysis of the interactions among students and a GAI chatbot. British Journal of Educational Technology, 56, 2125–2145. https://doi.org/10.1111/bjet.13611
- Güner, H., & Er, E. (2025). AI in the classroom: Exploring students’ interaction with ChatGPT in programming learning. Education and Information Technologies, 30, 12681–12707. https://doi.org/10.1007/s10639-025-13337-7
- Jaiswal, A., & Nanda, G. (2026). More than getting the answer: How students engage with generative AI in technical problem solving. International Journal of STEM Education, 13, Art. 58. https://doi.org/10.1186/s40594-026-00646-7
- Klar, M. (2025). Using ChatGPT is easy, using it effectively is tough? A mixed methods study on K-12 students’ perceptions, interaction patterns, and support for learning with generative AI chatbots. Smart Learning Environments, 12, Art. 32. https://doi.org/10.1186/s40561-025-00385-2
- Kock, Z.-J., Salinas-Hernández, U., & Pepin, B. (2025). Engineering students’ initial use schemes of ChatGPT as an instrument for learning. Digital Experiences in Mathematics Education, 11, 192–218. https://doi.org/10.1007/s40751-025-00169-w
- Liu, J., Keane, T., Sun, D., Yang, Y., & Yang, Y. (2025). Design and evaluation of ChatGPT-MWPS: An AI-enhanced learning system for improving primary students’ mathematical word problem solving. Smart Learning Environments, 12, Art. 68. https://doi.org/10.1186/s40561-025-00419-9
- McGalliard, W., & Otten, S. (2025). AI responses to challenging problems and educator responses to AI availability. Digital Experiences in Mathematics Education, 11, 319–332. https://doi.org/10.1007/s40751-024-00167-4
- Ng, D. T. K., Tan, C. W., & Leung, J. K. L. (2024). Empowering student self-regulated learning and science education through ChatGPT: A pioneering pilot study. British Journal of Educational Technology, 55, 1328–1353. https://doi.org/10.1111/bjet.13454
- Noster, N., Gerber, S., & Siller, H.-S. (2024). Pre-service teachers’ approaches in solving mathematics tasks with ChatGPT. Digital Experiences in Mathematics Education, 10, 543–567. https://doi.org/10.1007/s40751-024-00155-8
- Pepin, B., Buchholtz, N., & Salinas-Hernández, U. (2025). A scoping survey of ChatGPT in mathematics education. Digital Experiences in Mathematics Education, 11, 9–41. https://doi.org/10.1007/s40751-025-00172-1
- Song, Y., Huang, L., Zheng, L., Fan, M., & Liu, Z. (2025). Interactions with generative AI chatbots: Unveiling dialogic dynamics, students’ perceptions, and practical competencies in creative problem-solving. International Journal of Educational Technology in Higher Education, 22, Art. 12. https://doi.org/10.1186/s41239-025-00508-2
- Su, C. S., Hsu, C. C., & González Campos, J. A. (2026). ChatGPT as a resource to strengthen mathematics teaching and learning: A systematic review. Journal of Computer Assisted Learning, 42, Art. e70241. https://doi.org/10.1002/jcal.70241
- Turmuzi, M., Azmi, S., & Kertiyani, N. M. I. (2026). ChatGPT in school mathematics education: A systematic review of opportunities, challenges, and pedagogical implications. Teaching and Teacher Education, 170, Art. 105286. https://doi.org/10.1016/j.tate.2025.105286
- Urhan, S., Gençaslan, O., & Dost, Ş. (2026). Is ChatGPT a rational assistant for university students during mathematical reasoning? Science & Education. https://doi.org/10.1007/s11191-026-00725-9
- Wang, D., Shan, D., Ju, R., Kao, B., Zhang, C., & Chen, G. (2025). Investigating dialogic interaction in K12 online one-on-one mathematics tutoring using AI and sequence mining techniques. Education and Information Technologies, 30, 9215–9240. https://doi.org/10.1007/s10639-024-13195-9
- Yang, M., Jiang, S., Li, B., Herman, K., Luo, T., Chappell Moots, S., & Lovett, N. (2025). Analysing nontraditional students’ ChatGPT interaction, engagement, self-efficacy and performance: A mixed-methods approach. British Journal of Educational Technology, 56, 1973–2000. https://doi.org/10.1111/bjet.13588
- Yoon, H., Hwang, J., Lee, K., Roh, K. H., & Kwon, O. N. (2024). Students’ use of generative artificial intelligence for proving mathematical statements. ZDM – Mathematics Education, 56, 1531–1551. https://doi.org/10.1007/s11858-024-01629-0
- Zhou, R., He, X., Fan, Q., Li, Y., Li, Y., Xiao, X., & Fang, J. (2025). Exploring ChatGPT-facilitated scaffolding in undergraduates’ mathematical problem solving. Journal of Computer Assisted Learning, 41, Art. e70077. https://doi.org/10.1111/jcal.70077
Copyright (c) 2026 Valeria Yekti Kwasaning Gusti
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Education and Talent Development Center of Indonesia (ETDC Indonesia)
e-mail: kognitif@etdc.org, website : https://etdc-indonesia.com
Kognitif: Jurnal Riset HOTS Pendidikan Matematika dengan Situs: https://etdci.org/journal/kognitif berlisensi Creative Commons Attribution-ShareAlike 4.0 International License
Most read articles by the same author(s)
- Valeria Yekti Kwasaning Gusti , Thesa Kandaga, Suci Nurhayati, Erna Risnawati, Analysis of Guru Penggerak Program: Teacher Satisfaction and Method Implementation Across Different Demographics , Kognitif: Jurnal Riset HOTS Pendidikan Matematika: Vol. 5 No. 1 (2025): January - March 2025
.png)
