Mental effort detection using EEG data in E-learning contexts

Abstract E-learning becomes an alternative learning mode since the prevalence of the Internet. Especially, the advance of MOOC (Massive Open Online Course) technology enables a course to enroll tens of thousands of online learners. How to improve learners' online learning experiences on MOOC platforms becomes a crucial task for platform providers. In this research, based on Cognitive Load Theory, we built a system to capture and tag a user's mental states while s/he is watching online videos with a commercial EEG device, and used different normalization schemes and time window lengths to process EEG signals recorded from the EEG device. Finally, we adopted different supervised learning algorithms to train and test the classifiers, and then evaluated their classification performance. The results show that the proposed approach can effectively process EEG data to train classifiers, which achieve high accuracy, precision and recall rates compared with those of previous studies. This system can effectively facilitate users' self-awareness of mental efforts in online learning contexts to enable the automatic feedback in synchronous and asynchronous learning contexts, especially taking MOOCs as an example.