In-classroom learning analytics based on student behavior, topic and teaching characteristic mining

• Published in: Pattern recognition letters 2020-01, Vol.129, p.224-231
• Main Authors: Yang, Bohong, Yao, Zeping, Lu, Hong, Zhou, Yaqian, Xu, Jinkai
• Format: Article
• Language: English
• Subjects: Audio analysis; Classrooms; Correlation analysis; Feature extraction; Sequential mining; Speech; Speech recognition; Student behavior analysis; Students; Teachers; Teaching; Topic modeling
• ISSN: 0167-8655; 1872-7344
• DOI: 10.1016/j.patrec.2019.11.023

•Analyze the students’ behavior together with teaching contents and characteristic.•Focus on the ratio of students paying attention to the teaching contents.•Extract the teaching characteristic and topics from in-classroom videos.•Represent the teaching characteristic by extracting features from teacher’s audio.•Analyze the students’ behavior on different topics extracted from audio information. The automatic analysis of students’ in-classroom behavior is valuable to evaluate the effect of teaching. Recent studies of in-classroom video analysis mainly focus on lecture content, positions and identities of students. In this paper, we propose to analyze the students’ concentration degree to the teacher or teaching content. Specifically, we detect students’ faces, track faces, and analyze the students’ behavior, i.e. raising or downing faces and corresponding head orientations to the teacher, teaching content or not. Besides, texts are obtained from the teacher’s speech and the course topics taught in the class are extracted. Audio features of the teacher’s speech are extracted and analyzed. Finally, the correlation of the students’ concentration degree with the course topics, audio features are analyzed. This analysis can help teachers find the effective teaching characteristic to better improve students’ concentration degree.