Inferring Student's Attention in a Machine Learning Approach: A Feasibility Study

Jiachun Li, Ruiqi Li, Yuting Zhou, Junlin Xian, Xiong Zhang, Xiaojun Hei

Abstract: It is important that students should learn with full attention to achieve desired outcomes. In this paper, we propose a multi-modal assistant system for intelligent learning, which may capture and analyze the video and audio of student's learning process. We design and implement a machine learning framework to infer student's attention in order to effectively help the teacher to facilitate appropriate learning activities. Such capacity may also help achieve personalized learning recommendation for students. Our preliminary study demonstrate the feasibility of this multi-modal inference of attention in order to develop effective learning analytic towards formative assessment.