Proceedings of the E-Learning and Smart Engineering Systems (ELSES 2025)

<Previous Article In Volume
Next Article In Volume>

Emotion-Aware Adaptive Learning: Enhancing Engagement and Performance in STEM Education Using AI-Powered Emotion Analysis

Authors
Nisrine El Ayat1, *, Mohammed Boutalline1, Adil Tannouche2, Hamid Ouanan3
1Engineering Laboratory for Intelligent Technologies and Transformation (ELITT-Lab), Higher School of Technology, University Abdelmalek Essaadi, Tetouan, Morocco
2Laboratory of Engineering and Applied Technology, Higher School of Technology of Beni Mellal, Sultan Moulay Slimane University, Beni Mellal, Morocco
3Information Processing and Decision Support Laboratory, National School of Applied Sciences of Beni Mellal, Sultan Moulay Slimane University, Beni Mellal, Morocco
*Corresponding author. Email: n.elayat@uae.ac.ma
Corresponding Author
Nisrine El Ayat
Available Online 2 April 2026.
DOI
10.2991/978-94-6239-634-0_21How to use a DOI?
Keywords
Adaptive learning; emotion recognition; AI in education; deep learning; affective computing; intelligent tutoring systems
Abstract

Adaptive learning systems that monitor emotions have attracted interest due to their capabilities to customize educational experiences. The process of selecting optimal emotion recognition models faces challenges due to discrepancies in accuracy levels along with computational constraints and requirements for real-time learning capabilities. The researchers conduct a comparative evaluation between existing AI emotion recognition approaches for adaptive learning which includes deep learning models and traditional machine learning methods alongside multimodal fusion techniques.

This research examines various methodologies starting with CNNs used to detect facial expressions followed by LSTM and transformer methods for physiological and textual analysis together with hybrid approaches that merge multiple modalities. An evaluation of each technique relies on accuracy, computational efficiency, scalability, and real-time capability within e-learning systems. The research also investigates both ethical standards and privacy challenges that emerge from using AI emotion analysis in educational contexts.

By providing a benchmark analysis of AI-driven emotion recognition models, this paper aims to guide future research and development in adaptive learning systems. Our finding identified key strengths and limitations of different approaches that can lead to effective integration of emotion analysis within personalized learning modules across STEM education.

Copyright
© 2026 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the E-Learning and Smart Engineering Systems (ELSES 2025)
Series
Atlantis Highlights in Social Sciences, Education and Humanities
Publication Date
2 April 2026
ISBN
978-94-6239-634-0
ISSN
2667-128X
DOI
10.2991/978-94-6239-634-0_21How to use a DOI?
Copyright
© 2026 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

risenwbib
TY  - CONF
AU  - Nisrine El Ayat
AU  - Mohammed Boutalline
AU  - Adil Tannouche
AU  - Hamid Ouanan
PY  - 2026
DA  - 2026/04/02
TI  - Emotion-Aware Adaptive Learning: Enhancing Engagement and Performance in STEM Education Using AI-Powered Emotion Analysis
BT  - Proceedings of the E-Learning and Smart Engineering Systems (ELSES 2025)
PB  - Atlantis Press
SP  - 261
EP  - 272
SN  - 2667-128X
UR  - https://doi.org/10.2991/978-94-6239-634-0_21
DO  - 10.2991/978-94-6239-634-0_21
ID  - Ayat2026
ER  -