Sentiment Analysis on Students’ Evaluation of Higher Educational Institutions

Abstract

Sentiment analysis is the method of identifying and classifying the views of users from text documents into different sentiments, such as positive, negative or neutral. Sentiment analysis can be employed to extract structured and informative knowledge from unstructured text pieces. This knowledge can serve as an important source of information for decision support systems and individual decision makers. Sentiment analysis plays an important role in many fields like education, where student input is crucial for assessing the effectiveness of educational institutions. In this paper, we present a machine learning based approach to sentiment analysis on students’ evaluation of higher educational institutions. We analyze a corpus containing approximately 700 student reviews written in Turkish, with the use of conventional text representation schemes and machine learning classifiers. In the experimental analysis, three conventional text representation schemes (i.e., term-presence, term-frequency, TF-IDF scheme) and three N-gram models (1-gram, 2-gram and 3-gram) have been considered in conjunction with four classifiers (i.e., support vector machines, Naïve Bayes, logistic regression, and random forest algorithm). The predictive performance of four ensemble learners (i.e., AdaBoost, Bagging and Random Subspace and voting algorithm) have been also evaluated. The empirical results indicate that machine learning based approach yields promising results on students’ evaluation of higher educational institutions.