Analyzing Recorded Video to Evaluate How Engaged and Emotional Students Are in Remote Learning Environments

The prevalence of distance learning has led to an increasing concern regarding the dropout rate in educational environments. However, efforts are being made to enhance the quality of learning in academic institutions by changing learning platforms and teaching methods. Many unresolved problems exist, such as increasing school dropout rates and little attention to students’ emotional state and health conditions. The proposed solution involves analyzing recorded student videos, which will provide valuable insights into student emotion and engagement and help to reduce the dropout rate. This paper proposes a new approach to assessing students’ engagement and emotional states in distance learning environments without direct interaction. This study suggests a system for analyzing student-recorded video sequences in remote learning scenarios. The proposed approach combines advanced algorithms and machine learning methods to assess students’ levels of engagement and identify their emotions. The study’s findings show how an intelligent application may be created to assist educators in evaluating the feelings and engagement of their students. For instructors, this application is a valuable resource. It gives them insightful information on the experiences of their students and helps them adjust their teaching methods accordingly.