A Multimodal Monitoring System with XGBoost Classifier for Optimizing Student Engagement in Online Learning

Online learning has gained significant momentum due to globalization and the COVID-19 pandemic, but maintaining student engagement in this environment remains challenging. Traditional methods like self-reports and manual observations often miss subtle attentiveness cues, which necessitate more advanced tools for assessing engagement. This paper introduces a system that integrates computer vision techniques with an XGBoost classifier to analyze behaviors such as facial expressions, hand movements, mobile phone usage, and head poses via a standard webcam. The system outperformed traditional methods by achieving a 96.7% accuracy after validating on a dataset of 4,000 records. It generates detailed, anonymous reports, which offer current insights into student involvement while maintaining privacy. The system is resource-efficient and scalable to make it adaptable to various educational settings. A user-friendly interface enables seamless integration with e-learning platforms, allowing instructors to make data-driven interventions. This study also discusses the ethical and privacy concerns of such systems to balance the need for effective monitoring with the protection of student autonomy.