YOLOv8-based emotion recognition for effective student engagement assessment in online learning environments

The rise in popularity of online learning has highlighted the importance of finding a reliable way to assess student engagement. Traditional methods are not effective enough to monitor participation properly in an online learning environment. This lack of visibility can lead to unnoticed challenges faced by students, ultimately impeding their progress and development. Our research suggests a unique system for capturing and examining students' emotions during virtual lectures. We conducted a thorough assessment of this model by conducting training sessions, tests, and comparisons with existing models. Our findings revealed that the Yolov8 architecture-based model outperformed other models in recognizing student engagement. Further, our proposed model outperforms many existing works in engagement recognition on the same dataset.