Predicting Student Seating Distribution Based on Social Affinity

摘要

Learning students social affinity and modeling their social networks are beneficial for instructors to design proper pedagogical strategies. Students seating distribution contains social data and can be used for analysing their social relationships. In this paper, we propose a method to automatically construct the class social network and predict the position of a student's seat in class. First, we determine the positions of each student in a classroom by utilizing the center projection principle and linear fitting algorithms. The intimate relationship between students is captured to model their social network based on Euclidean distance. Then, we learn the social affinities from the Social Affinity Map (SAM) which clusters the relative positions of surrounding students. Based on this, students' seating distribution can be predicted successfully with accuracy reaching 82.1%.