Enhancing Online Learning: A Multimodal Approach for Cognitive Load Assessment

Online learning has become increasingly popular in recent years, but the frequent occurrence of cognitive overload has been notably impacting both the learning experience and effectiveness. Therefore, based on optimizing online learning, this study proposes a research framework for cognitive load assessment of online learning based on three modal data: electroencephalography (EEG), eye tracking, and face. Following this framework, a neural network was used to construct a cognitive load assessment model for online learning that integrates multimodal data. After validation, the assessment accuracy of the model reaches 91.52%. In addition, the results based on multimodal data analysis can be used as a reference for the development of learning resources and the optimization of online courses in intelligent online learning platforms. The assessment model constructed in this study can also be applied to the online learning platform, which is expected to realize prescription-adaptive online learning based on cognitive load assessment. Due to current research limitations, only specific thematic learning models have been explored. Future research will focus on model fine-tuning, complex learning scenarios and themes designing and expansion of research scale to enhance the model's generalization capabilities.