Sentiment Analysis to Measure Mobile Legend Application User Reviews Using Naive Bayes, SVM, Random Fores Algorithms, Decision Tree, dan Logistic Regression

Abstract

This study aims to analyze the sentiment of Mobile Legend application users on the Google Play Store using machine learning algorithms, including Naïve Bayes, Support Vector Machine (SVM), Random Forest, Decision Tree, and Logistic Regression. From the results of scraping data on 3989 reviews, it was found that Mobile Legend users in Indonesia tend to be neutral towards this application, with 1265 neutral comments, 1115 positive comments, and 1204 negative comments. Through model evaluation, SVM showed the highest accuracy of 87%, outperforming other algorithms such as Random Forest, Naïve Bayes, Decision Tree, and Logistic Regression. The conclusion of this study shows that SVM is an excellent choice for conducting sentiment analysis on Mobile Legend application user reviews. These results can be a guide for developers to understand user responses and improve app quality based on sentiment analysis findings.