Evaluating E-learning Engagement Through EEG Signal Analysis with Convolutional Neural Networks

Amidst the COVID-19 pandemic, online e-learning platforms have experienced a surge in popularity, serving a diverse audience across multiple subjects. Nevertheless, the absence of learner-centric approaches and efficient learning validation on these platforms has become a concern within the online learning community. This has led to an increased demand for personalized learning recommendations for both learners and educational materials. In response to these challenges, we propose an innovative solution that utilizes real-time EEG data acquired from individuals wearing EEG headsets while participating in online courses. Our approach centers on a deep learning convolutional neural network (CNN) model, which adeptly classifies these EEG signals with an impressive accuracy rate of 70%. This remarkable performance underscores the speed and precision of our developed models in handling e-learning EEG signals, presenting a promising resolution to prevailing e-learning validation issues. Beyond classification, our work introduces an automated framework that continuously tracks users’ learning progress and provides invaluable recommendations for e-learning materials, effectively elevating the overall learning experience. By leveraging this framework, we envision a transformative impact on e-learning platforms, as it not only validates user learning more effectively but also offers personalized recommendations, creating a more efficient and user-centric e-learning environment. As a result, our research contributes significantly to the advancement of e-learning practices, especially during challenging times like the pandemic, where remote learning has become increasingly prevalent.