AI-Supported Tutoring and Cognitive Learning Styles in an Engineering Mathematics Refresher Course

Authors

  • Gustav Potgieter North-West University
  • Brandt Klopper North-West University
  • Liezl van Dyk North-West University
  • Liandi van den Berg North-West University

DOI:

https://doi.org/10.54337/irspbl-11060

Keywords:

AI tutoring, Engineering education, Mathematics refresher course, Cognitive profiles, Student engagement

Abstract

Many second-year engineering students enter advanced mathematics courses with gaps in foundational knowledge, leading to high failure rates and limited progression in engineering studies. Artificial intelligence (AI)-driven tutoring has emerged as a potential intervention to address these gaps by providing structured support and real-time feedback. This study investigates the effectiveness of AI-supported tutoring in a one- week intensive refresher course, with a focus on how cognitive learning styles influence engagement. 

Using Neethling Brain Instrument (NBI) cognitive profiling, Google Form surveys, and interaction data from the Mindjoy tutorbot, the analysis revealed that students with structured, analytical preferences (L1) engaged most frequently with the AI tutor, while creative (R1) and relational (R2) students engaged less. Students who made frequent use of the AI tutor reported increased confidence in problem-solving. These findings highlight the need for AI tutoring systems to adapt to diverse cognitive profiles to maximise engagement and learning outcomes. 

References

Bringula, R., Reguyal, J. J., Tan, D. D., & Ulfa, S. (2021). Mathematics self-concept and challenges of students in an online learning environment during COVID-19 pandemic. Smart Learning Environments, 8, 22.

Ding, L., Li, T., Jiang, S., & Gapud, A. (2023). Students’ perceptions of using ChatGPT in a physics class as a virtual tutor. International Journal of Educational Technology in Higher Education, 20, 63.

Green, S., & Carter, L. (2022). Between AI and learning science: The evolution and commercialization of intelligent tutoring systems. AI Education Review, 12(1), 45–60.

Mindjoy. (2025). Mindjoy. https://www.mindjoy.com/

Neethling, K. (2025). Neethling Brain Instruments. https://www.nbi.org.za/

Vlachogianni, P., & Tselios, N. (2021). Perceived usability evaluation of educational technology using the System Usability Scale (SUS): A systematic review. Journal of Research on Technology in Education, 53(1), 1– 17.

Wang, X., Huang, R. T., Martin, F., et al. (2024). The efficacy of artificial intelligence-enabled adaptive learning systems from 2010 to 2022 on learner outcomes: A meta-analysis. Journal of Educational Computing Research.

Front cover for the proceedings of the 10th International Research Symposium on Problem-Based Learning. With the title "Anchoring conversations (IRSPBL 2025)

Downloads

Published

14-11-2025

How to Cite

Potgieter, G., Klopper, B., van Dyk, L., & van den Berg, L. (2025). AI-Supported Tutoring and Cognitive Learning Styles in an Engineering Mathematics Refresher Course. Proceedings from the International Research Symposium on Problem-Based Learning (IRSPBL). https://doi.org/10.54337/irspbl-11060

Issue

2025: 10th International Research Symposium on Problem-Based Learning (IRSPBL 2025)

Section

Theme 3: Technology, AI, and Digital Learning in STEM Education

License

Creative Commons License

This work is licensed under a Creative Commons Attribution-NoDerivatives 4.0 International License.