Students Emotion and Distraction Detection While Adopting E-Learning Approach

Abstract

Currently, e-learning has changed the way students’ study by providing high-quality education that is not restricted by place or time. Mobile phones, tablets, laptops, and desktop computers are some of the products that make online learning easier. These devices were used for mandatory online learning due to the COVID-19 pandemic. However, because the e-learning approach prevents an instructor from actively observing a group of students, they may become distracted for many reasons, significantly reducing their learning potential. This paper proposes an intelligent system called the Intelligent E-Learning Monitoring System (IELMS) that helps faculty members keep track of such students and supports them in improving their performance. Convolutional neural network (CNN) techniques are utilized to detect emotions, and once the optimum algorithm for detecting emotions has been identified, it is fused into the model that detects an online learner’s distraction. The fused model produces logs of distraction and emotion. These logs will assist the teaching community in identifying underperforming online learners and facilitating counseling.