Affective Student Engagement Detection using Machine Learning: A Systematic Survey on Methods, Modalities and Learning Environments
Journal of Trends in Computer Science and Smart Technology · 04.07.2026 · 8 (3) · 517-537
DOI: 10.36548/jtcsst.2026.3.005 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Trends in Computer Science and Smart Technology, online erschienen am 04.07.2026. Verfasst von Shruthi H K. und 3 weiteren Autor:innen. Die Arbeit nennt 26 Literaturangaben.
Abstract (Originalsprache)
Student engagement is one of the essential factors an academic success, but tracking the internal affective conditions of learners is a complicated problem in the modern educational environment. The results show that there has been a major shift from using simple behavioral monitoring to more complex affective computing, though visual modalities (63%) are the most used because of their scalability and non-invasive nature. Nevertheless, the results highlight an increased use of multimodal fusion and deep learning systems, particularly, hybrid models (e.g. CNN-LSTM), to effectively learn fine-grained academic emotions (e.g. frustration, boredom, and enjoyment) in online, traditional, and hybrid classes. Furthermore, the review shows a methodological shift towards “in-the-wild” study designs with an emphasis on ecological validity in authentic and uncontrolled learning settings. Although there is significant technical advancement, major gaps remain in establishing standardized benchmark datasets, explaining AI models, and deploying ethical, privacy-protecting frameworks. Overall, this survey highlights that future developments should focus on promoting more responsive, inclusive, and empathetic learning through the development of real-time, pedagogically validated intervention systems.
Zitieren
APA
K., S. H., J., J., M., V., & Gondkar, R. R. (2026). Affective Student Engagement Detection using Machine Learning: A Systematic Survey on Methods, Modalities and Learning Environments. Journal of Trends in Computer Science and Smart Technology, 8(3), 517-537. https://doi.org/10.36548/jtcsst.2026.3.005
Vancouver
K. SH, J. J, M. V, Gondkar RR. Affective Student Engagement Detection using Machine Learning: A Systematic Survey on Methods, Modalities and Learning Environments. Journal of Trends in Computer Science and Smart Technology. 2026;8(3):517-537. doi:10.36548/jtcsst.2026.3.005
BibTeX
@article{K2026,
author = {K., Shruthi H and J., Jayapriya and M., Vinay and Gondkar, Raju Ramakrishna},
title = {Affective Student Engagement Detection using Machine Learning: A Systematic Survey on Methods, Modalities and Learning Environments},
journal = {Journal of Trends in Computer Science and Smart Technology},
year = {2026},
volume = {8},
number = {3},
pages = {517--537},
doi = {10.36548/jtcsst.2026.3.005}
}
EUVIMED