An Efficient Prediction Model for Student’s Attention in Online Education using Machine Learning

Due to the pandemic and technological advancements, many students have willingly enrolled in various online courses rather than visiting traditional classroom settings. To evaluate the success of online learning, it is critical to understand how students interact with their courses. Conventional methods of assessing online learning activities primarily focus on exam outcomes and student feedback. Online learning presents challenges since students' access to specific knowledge is limited by their attendance and exam performance. A proficient educator will monitor the students' attention spans, sustain concentration, and draw attention to places where students need further explanation. Enhancing the quality of remote learning was the primary goal of this study. We offer a method that uses a brain-computer interface (BCI) to monitor objective brain activity to quantify students' level of attention during remote learning. The benchmark dataset was used for the analysis. The proposed model's performance analysis has been analyzed using different metrics. The results obtained in the experiments depict that the proposed model effectively performs better than other cotemporary models in the state of the art.