Lexicon Based Sentiment Analysis of Students’ Feedback Comments

Abstract

Sentiment analysis is used to determine sentiments, emotions and attitude of user. In educational evaluation, sentiment analysis is implemented in teaching evaluation in order to explore the answers obtained from open-ended questions. Students’ feedback has numerous advantages in education, however, analyzing feedback while teaching is both stressful and time consuming. To address this problem, we propose to analyze the students’ text feedback automatically using lexicon based sentiment analysis to predict teaching performance. A database of English sentiment words is created as a lexical source to get the polarity of words. By analyzing the sentiment information extracting from students’ feedback related to teaching style of their teachers, we are able to determine whether the students’ text feedback are positive or negative opinion. This system shows the opinion result of teachers that is represented as either strongly negative, negative, weakly negative, strongly positive, positive, weakly positive or neutral.