Realtime Online Class Engagement Monitoring System Using Machine Learning

– In the rapidly evolving landscape of digital education, sustaining authentic student engagement in online classrooms remains a critical challenge. This research proposes a Realtime Online Class Engagement and Monitoring System that transcends traditional attendance or attention-tracking tools by integrating multimodal analytics, affective computing, and adaptive feedback mechanisms. The system utilizes a combination of webcam-based emotion recognition, eye-gaze tracking, voice activity analysis, and interactive behavioural metrics to measure student engagement dynamically during live sessions. Unlike conventional systems that merely detect presence, the proposed model interprets cognitive attention patterns and emotional states to generate personalized engagement scores in real time.