User Sentiment Analysis and Review Rating Prediction for the Blended Learning Platform App

Abstract

Understanding how to assess the learners' evaluation has become an essential topic for both academics and practitioners as blended mobile learning applications have proliferated. This study examines users' sentiment and predicts the review rating of the blended learning platform app using machine learning (ML) techniques. The data for this study came from Google Play Store reviews of the Google Classroom app. The VADER and AFINN sentiment algorithms were used to determine if the filtered summary sentences were positive, neutral, or negative. In addition, five supervised machine learning algorithms were used to differentiate user evaluations of the Google Classroom app into three sentiment categories in the current study. According to the results of this investigation, the majority of reviews for this app were negative. While all five machine learning algorithms are capable of correctly categorizing review text into sentiment ratings, the random logistic regression outperforms in terms of accuracy.