Analyzing and Predicting Learner Sentiment Toward Specialty Schools Using Machine Learning Techniques

Abstract

The objective of the research is to use machine learning techniques to evaluate and predict learners' sentiment toward specialty school. The current study used the Yelp website's reviews to obtain data on specialty schools after filtering. Following cleaning, the filtered summary sentences were rated as positive, neutral, or negative sentiments using the AFINN and VADER sentiment algorithms. In addition, to split learner ratings of specialty schools into three sentiment categories, the current study also used four supervised machine learning techniques. The majority of ratings for specialty schools were favorable, according to the findings of the present study. Furthermore, while all of the techniques (decision tree, K-neighbors classifier, logistic regression, and SVM) can accurately classify review text into sentiment class, and SVM outperforms in terms of high accuracy. Specialty educational institutes will be able to better understand learners' psychological sentiments based on the findings of the study, allowing them to improve and adjust their services.