Volume 4, 2026 – Issue 3 
Emotion Recognition by Deep Learning to Support Mathematics Learning and Reduce Math Anxiety: A Review of Pedagogical Approaches
Vikas Jangra
1* and Sumeet Gill
2
Department of Mathematics, Maharshi Dayanand University Rohtak-124001, Haryana, India
* Corresponding author: vikasjangra96.rs.maths@mdurohtak.ac.in
DOI: 10.5281/zenodo.23584934
Abstract
Mathematics learning is affected by various achievement emotions such as enjoyment, boredom, frustration, and anxiety. Math anxiety can decrease motivation, perseverance, working-memory capacity, and performance while the teacher struggles to watch each individual student. This conceptual review consolidates research on mathematics-related emotions, emotion recognition based on deep learning, affective tutoring, and anxiety reduction with the help of artificial intelligence. This paper tries to answer two questions: (1) How can emotion recognition based on deep learning be used in math education to support learning and decrease anxiety? (2) What kind of technical, pedagogical, and ethical guidelines are necessary for using it? On the basis of the literature reviewed, a human-centric approach with three layers: sensing, interpretation, and pedagogical response is proposed. The visual, vocal, physiological, and interaction signals are processed into probability-based affect estimates which could be used for adjusting the pace, providing hints, scaffolding, and supportive feedback. Although it is possible to recognize emotions in a classroom, the performance of existing solutions depends on the task, dataset, emotion labels, and context and does not show any evidence of anxiety reduction. Thus, the role of emotion-aware artificial intelligence should be complementary to teacher’s judgments.
Keywords: affective computing, deep learning, emotion recognition, mathematics education, math anxiety, intelligent tutoring systems
Published
2026/10/31
—
Section
Research Papers
How to Cite (APA)
Download Citation: EndNote/Zotero/Mendeley (RIS)
References
Barrón Estrada, M. L., Zatarain Cabada, R., & Hernández Pérez, Y. (2014). Intelligent tutor with emotion recognition and student emotion management for math performance. Revista Electrónica de Investigación Educativa, 16(3), 88–102.
Dimaunahan, R. G. P., Tiu, J. K. M., Sumalbag, M. I. B., & Bardiano, E. A. Q. (2026). The impact of ChatGPT on reducing anxiety and enhancing mathematical performance. DLSU Senior High School Research Congress Conference Proceedings, 5(5), Article 2. https://animorepository.dlsu.edu.ph/dlsushsresconproceedings/vol5/iss5/2/
Etcuban, J. O. (2025). The use of ChatGPT in addressing algebra anxiety and promoting confidence. International Electronic Journal of Mathematics Education, 20(2), Article em0825. https://doi.org/10.29333/iejme/16008
Kaur, R. (2025). Managing math anxiety with AI: Innovative approach of AI-assisted learning (Master’s thesis, Unitec Institute of Technology). ResearchBank. https://hdl.handle.net/10652/6773
Liu, J., & Wang, H. (2022). Analysis of educational mental health and emotion based on deep learning and computational intelligence optimization. Frontiers in Psychology, 13, Article 898609. https://doi.org/10.3389/fpsyg.2022.898609
Mastorodimos, D., & Chatzichristofis, S. A. (2019). Studying affective tutoring systems for mathematical concepts. Journal of Educational Technology Systems, 48(1), 14–50. https://doi.org/10.1177/0047239519859857
Polydoros, G., Antoniou, A. S., Vasileiou, I., & Polydoros, C. (2025). Teaching and learning high school mathematics in the post-COVID-19 era: Investigating the emotion factor. Frontiers in Psychology, 16, Article 1617765. https://doi.org/10.3389/fpsyg.2025.1617765
Schukajlow, S., Rakoczy, K., & Pekrun, R. (2023). Emotions and motivation in mathematics education: Where we are today and where we need to go. ZDM–Mathematics Education, 55(2), 249–267. https://doi.org/10.1007/s11858-022-01463-2
Sudhandradevi, P., & Bhuvaneswari, V. (2025). Facial recognition with advanced emotional states: A CNN-RF and CNN-LSTM hybrid framework for stress, frustration, and confidence. TPM–Testing, Psychometrics, Methodology in Applied Psychology, 32(S3), 436–450.
Wang, H., Wang, C., Xu, H., Bao, C., & Xu, X. (2026). Enhancing real-time facial emotion recognition in classrooms via Attention-ResNet optimization. The Visual Computer, 42, Article 46. https://doi.org/10.1007/s00371-025-04265-1
Whitehill, J., Serpell, Z., Lin, Y.-C., Foster, A., & Movellan, J. R. (2014). The faces of engagement: Automatic recognition of student engagement from facial expressions. IEEE Transactions on Affective Computing, 5(1), 86–98. https://doi.org/10.1109/TAFFC.2014.2316163
Yuan, Q. (2022). Research on classroom emotion recognition algorithm based on visual emotion classification. Computational Intelligence and Neuroscience, 2022, Article 6453499. https://doi.org/10.1155/2022/6453499
Zhang, N., & Leong, W. Y. (2025). Intelligent emotional computing with deep convolutional neural networks: Multimodal feature analysis and application in smart learning environments. Eurasia Journal of Mathematics, Science and Technology Education, 21(8), Article em2680. https://doi.org/10.29333/ejmste/16661
About the authors
- Vikas Jangra is a Ph.D. Research Scholar in the Department of Mathematics at Maharshi Dayanand University, Rohtak, Haryana, India. He holds an M.Sc. in Mathematics and is pursuing his Ph.D. in the area of Artificial Intelligence-based mathematical modelling. His research interests include Artificial Intelligence, Machine Learning, Deep Learning, Computer Vision, Mathematical Modelling, Multimodal Emotion Recognition, Human–Computer Interaction, and Medical Image Fusion. His research focuses on developing AI-based models and computational approaches for emotion recognition and image processing applications. He has published research papers and book chapters in the areas of Artificial Intelligence, Deep Learning, Emotion Recognition, and Medical Image Fusion.
vikasjangra96.rs.maths@mdurohtak.ac.in
↩︎ - Sumeet Gill is a Professor and Head of the Department of Mathematics at Maharshi Dayanand University (MDU), Rohtak, Haryana, India. He holds a Ph.D. and has extensive academic and research experience in the fields of Artificial Intelligence, System Security, Computer Science, and related interdisciplinary areas. His research interests include Artificial Intelligence, Machine Learning, Neural Networks, Image Processing, and System Security. He has contributed to research through publications in reputed journals and conferences and has supervised research scholars in interdisciplinary areas. He has also undertaken various academic and administrative responsibilities at the university. His research reflects the application of computational and mathematical approaches to emerging problems in science and technology.
drsumeetgill@mdurohtak.ac.in
↩︎


