Emotion-Aware Learning Systems: A Computational-Educational Framework for Integrating Affective Computing into Educational Psychology

The increasing complexity of modern learning environments has underscored the critical role of learners’ emotional states in shaping cognitive performance, motivation, and long-term knowledge retention. Despite significant advances in both educational psychology and affective computing, a systematic integration of these domains into scalable learning systems remains underdeveloped. This study proposes a novel interdisciplinary framework for emotion-aware learning systems that bridges theoretical constructs from educational psychology with real-time affect detection and adaptive computational modeling. Drawing on established theories of emotion–cognition interaction, including control-value theory and self-regulated learning models, the proposed framework operationalizes affective states as dynamic variables within intelligent learning environments. The study introduces a multi-layer architecture combining multimodal emotion recognition—leveraging physiological signals, facial expression analysis, and behavioral interaction data—with adaptive pedagogical decision-making mechanisms. A hybrid modeling approach is employed, integrating machine learning algorithms with psychologically grounded rule-based systems to enhance interpretability and pedagogical alignment. Empirical validation is conducted through a controlled experimental design involving undergraduate learners in a digital learning environment. Results demonstrate statistically significant improvements in engagement (p < ۰.۰۱), learning efficiency (p < ۰.۰۵), and emotional regulation compared to non-adaptive baseline systems. Furthermore, the findings highlight the mediating role of emotional awareness in optimizing cognitive load and sustaining intrinsic motivation. This research contributes to both theory and practice by offering a rigorously grounded, computationally implementable model for emotion-aware education. It advances the field by moving beyond static personalization toward continuous, affect-driven adaptation, thereby opening new pathways for designing intelligent, human-centered learning technologies.

کلیدواژه ها:

Emotion-Aware Learning Systems ، Affective Computing ، Educational Psychology ، Adaptive Learning Environments ، Emotion Recognition ، Self-Regulated Learning