Use Topic Modeling to Understand Comments in Student Evaluations of Teaching

Abstract

Abstract Written comments in student evaluation of teaching offer a rich source of data for understanding instructors’ teaching and students’ learning experiences. However, most of previous researches on student evaluation of teaching have focused on the numeric ratings to close-ended questions, few researches tried to analyze the content of students’ written comments to open-ended questions, which normally involved a labor-intensive manual process of coding and categorizing. Such qualitative efforts prevent solutions on a large scale since it is almost impossible to go through all the textual data manually. Therefore, an innovative quantitative method that can analyze large corpus of data holds great promise. This paper proposed LDA method of topic modeling to discover important themes emerged in students’ written comments. We compared our results with findings in previous qualitative studies. We also investigated how these themes varied by course grade levels and course subjects. Our results provided first evidence that topic modeling can be an effective and efficient alternative to understand teaching and learning experiences through students’ written comments on a large scale.