Personalized learning environments aim to tailor instruction to individual needs, but most adaptive systems neglect the emotional states that strongly influence motivation, persistence, and comprehension. This research introduces a computer vision-based framework for emotion-aware personalization in adaptive learning systems. The objective is to create emotionally responsive platforms that adapt not only to performance data but also to learners’ affective experiences. The proposed method employs facial expression analysis and micro-gesture detection to classify emotions such as happiness, frustration, and fatigue. These emotional cues are integrated with the adaptive engine to deliver real-time instructional adjustments, including simplifying tasks, offering motivational messages, or suggesting breaks. A prototype system was developed and evaluated in a simulated learning environment, demonstrating that emotion-driven adaptations increase learner satisfaction, reduce frustration, and sustain engagement compared to conventional personalization approaches. The results show that incorporating affective signals into adaptive learning enriches learner models and creates a more human-centered educational experience. The study concludes that emotion-aware personalization supported by computer vision holds strong potential for advancing adaptive learning technologies, ensuring they are not only cognitively effective but also emotionally supportive. By addressing both performance and affective dimensions, the proposed approach paves the way toward adaptive learning systems that foster resilience, motivation, and deeper learning outcomes.

Adaptive Learning, Computer Vision, Emotion Recognition, Affective Computing, Intelligent Tutoring Systems, Personalized Education