Sentiment and Emotion Analyses for Malaysian Mobile Digital Payment Applications

Abstract

1. Sentiment and emotion analyses provide a quick and easy way to infer users' perceptions regarding products, services, topics and events, and thus rendering it useful to businesses and government bodies for effective decision making. In this paper, we describe the outcomes of sentiment and emotion analyses performed on a mobile payment app, Boost, which is available in the Google Play Store. A total of 2463 text reviews were gathered, however, after pre-processing, 1054 of these reviews were annotated and used for sentiment and emotion analyses. Four supervised learning algorithms, namely, Support Vector Machine, Naïve Bayes, Decision Tree and Random Forest were compared using Python. Accuracy and F1 scores indicate Random Forest to have outperformed all the other algorithms for both sentiment and emotion analyses. A vast majority of the reviews were found to contain anger for the negative sentiments, whereas joy was observed for the positive reviews.