Comparative Sentiment Analysis of App Reviews

TL;DR

This paper employs machine learning and NLP techniques to classify sentiment in app reviews, comparing models trained on Google reviews and tested on student reviews, highlighting the effectiveness of ensemble methods.

Contribution

It introduces a sentiment classification approach for app reviews using TF-IDF and ensemble learning, with a focus on university students' review behavior.

Findings

SVM achieved 93.37% accuracy on review classification.

Ensemble methods improved performance of LR and NB classifiers.

Tri-gram + TF-IDF scheme was most effective.

Abstract

Google app market captures the school of thought of users via ratings and text reviews. The critique's viewpoint regarding an app is proportional to their satisfaction level. Consequently, this helps other users to gain insights before downloading or purchasing the apps. The potential information from the reviews can't be extracted manually, due to its exponential growth. Sentiment analysis, by machine learning algorithms employing NLP, is used to explicitly uncover and interpret the emotions. This study aims to perform the sentiment classification of the app reviews and identify the university students' behavior towards the app market. We applied machine learning algorithms using the TF-IDF text representation scheme and the performance was evaluated on the ensemble learning method. Our model was trained on Google reviews and tested on students' reviews. SVM recorded the maximum accuracy(93.37\%), F-score(0.88) on tri-gram + TF-IDF scheme. Bagging enhanced the performance of LR and NB with accuracy of 87.80\% and 85.5\% respectively.