Fine-grained Analysis of Gender Bias in Student Evaluations

Abstract

The most widely applied method to evaluate an instructor’s performance in a course is by collecting numerical responses against a set of questionnaires about the instructor and the course, along with comments in free-form text. Published research results depict biases in the student evaluations of instructors in their ratings and comments. However, the research so far has not been directed at the fine-grained analysis of gender bias: the opinion (sentiments) of students towards qualitative metrics of their interaction with their instructors. This work-in-progress (WIP) proposes (a) a methodology to mine teaching evaluations and (b) an open-source tool to support educational establishments and students in executing empirical studies and exploratory analytics on the teaching evaluations.