Predicting student engagement in classrooms using facial behavioral cues

Abstract

Student engagement is the key to successful classroom learning. Measuring or analyzing the engagement of students is very important to improve learning as well as teaching. In this work, we analyze the engagement or attention level of the students from their facial expressions, headpose and eye gaze using computer vision techniques and a decision is taken using machine learning algorithms. Since the human observers are able to well distinguish the attention level from student’s facial expressions,head pose and eye gaze, we assume that machine will also be able to learn the behavior automatically. The engagement level is analyzed on 10 second video clips. The performance of the algorithm is better than the baseline results. Our best accuracy results are 10 % better than the baseline. The paper also gives a detailed review of works related to the analysis of student engagement in a classroom using vision based techniques.