Classification of Mobile Application User Ratings Based on Data from Google Play Store

Abstract

This research is a comparison using 3 (three) algorithms, namely Lo- gistic Regression, K-Nearest Neighbor, and Support Vector Machine in senti- ment analysis about the JMO application, as the main means for participants in the employment social security program, which plays a crucial role in providing services that meet participants' needs well. This research aims to compare three different classification algorithms for sentiment analysis in the Jamsostek mobile application. The process involves several stages, including data collection (Crawling), word separation (tokenizing), normalization, removal of common words (Stopword), and word simplification (Stemming). After the processing stage, the data is labeled and classified using a comparison of three algorithms. The results of the 3 tweet category algorithms tend to be positive and negative. From the Logistic Regression algorithm, the accuracy level achieved was 84.78%, the precision was 87.24%, and the recall was 62.16%, then the Support Vector Machine algorithm achieved an accuracy level was 89.13%, the precision was 86.67%, and the recall of 76.88%, and the KNN algorithm produced an ac- curacy level of 88.59%, precision of 91.07%, and recall of 71.88%.