Multi-Label Emotion Mining From Student Comments

Abstract

Science, Technology, Engineering, and Mathematics (STEM) education is gaining more attention not today but has been under research, and discussion for the past few decades. Factors that are considered for research include but not limited to the following, culture on campus, teaching and learning models, and student experience in classroom, gender bias, and stereotypes. One of the major factors is the teaching model adopted which have impact on the student learning styles and their experience in the classroom. Teaching models include traditional models, modern flipped class-room models, and active learning approaches. This study focuses on active learning approaches and their impact on students learning and experience. Light-weight team is an active learning approach, in which team members have little direct impact on each other's final grades, with significant long-term socialization. In this work we used data from end of course student evaluation. We propose extend our previous method for assessing the effectiveness of the Light-weight team teaching model, through automatic detection of emotions in student feedback in computer science course by creating multi-label for each text comment. The students are surveyed about their feelings and thoughts about teaching and learning models adopted and student experience in the classroom. Results show that implementation of these methods result in increased positivity in student emotions.