Sentiment analysis of student evaluations of teaching

Abstract

We used a sentiment analysis tool, VADER (Valence Aware Dictionary and sEntiment Reasoner), to analyze Student Evaluations of Teaching (SET) of a single course from three different sources: official evaluations, forum comments from another course, and an unofficial “reviews” site maintained by students. We compared the positive and negative valences of these sites; identified frequently-used key words in SET comments and determined the impact on positivity/negativity of comments that included them; and determined positive/negative values by question on the official course SET comments. Many universities use similar questions, which may make this research useful for those analyzing comments at other institutions. Previous published studies of sentiment analysis in SET settings are rare.