Online Classroom Evaluation System Based on Multi-Reaction Estimation

Abstract

Online learning is more convenient than traditional face-to-face teaching methods. However, during real-time online classes, it is difficult for teachers to observe the reactions of all students simultaneously. Herein, we introduce an online education classroom evaluation system that enables teachers to adjust the speed of their lessons based on students' reactions. We aim to develop a method that can evaluate student participation based on multi-reaction of students. In this study, the system estimates the head poses and facial expressions of students through the camera and uses the information as criteria for assessing student participation. The estimated result enables the class quality to be categorized into positive, negative, and neutral, thereby allowing teachers to rearrange the class contents. Finally, we evaluate the performance of our system by testing the accuracy of student reaction estimation and our classroom evaluation method. CCS CONCEPTS• Applied computing → Computer-assisted instruction.