A correlation analysis of the sentiment analysis scores and numerical ratings of the students in the faculty evaluation

Abstract

This paper aims to analyze the relationship between the students' numerical rating and the qualitative measure of the students' written comments in the faculty evaluation using sentiment analysis. The dataset which consists of the numerical ratings and students' feedback obtained from the faculty evaluation system was used in the experiment. An ensemble model which consists of five machine learning algorithms was used to analyze and identify the polarity of the written comments of the students. The overall sentiment score was computed for each faculty and was compared to the numerical score using the statistical technique, Pearson's correlation coefficient. The result indicates that there is significance but very small relationship between the numerical rating and the overall sentiment scores. Based on the result, universities and colleges should exploit written comments since it is rich with observations and insights about the performance and effectiveness of a teacher. Moreover, sentiment analysis technique can be used to identify students' feeling towards teaching.