Automated Analysis of Open-Ended Students’ Feedback Using Sentiment, Emotion, and Cognition Classifications

Abstract

Students’ feedback is pertinent in measuring the quality of the educational process. For example, by applying lexicon-based sentiment analysis to students’ open-ended course feedback, we can detect not only their sentiment orientation (positive, negative, or neutral) but also their emotional valences, such as anger, anticipation, disgust, fear, joy, sadness, surprise, or trust. However, most currently used assessment tools cannot effectively measure emotional engagement, such as interest level, enjoyment, support, curiosity, and sense of belonging. Moreover, none of those tools utilize Bloom’s taxonomy for students’ learning-level assessment. In this work, we develop a user-friendly application based on NLP to help the teachers understand the students’ perception of their learning by analyzing their open-ended feedback. This allows us to examine the sentiment and the embedded emotions using a customized dictionary of emotions related to education. The application can also classify the students’ emotions according to Bloom’s taxonomy. We believe our application will help teachers improve their course delivery.