<![CDATA[The development of digital technology has increased the use of online transportation applications in Indonesia, one of which is Gojek. User reviews on the Gojek application in the Google Play Store reflect the level of user satisfaction and dissatisfaction with the services provided. Therefore, sentiment analysis is needed to classify these reviews into positive and negative categories. This study aims to get the result and performance of Support Vector Machine (SVM) and random forest classification methods in sentiment analysis of Gojek user reviews. The data used are user reviews from January 2026 obtained through a scraping technique. The analysis stages include text processing, word weighting using TF-IDF, and hyperparameter optimization using the random search method. The results show that the SVM method achieved an accuracy of 86,78%, precision of 87,96%, recall of 86,23%, and F1-score of 87,09%. Meanwhile, the random forest method achieved an accuracy of 84,75%, precision of 82,87%, recall of 88,85%, and F1-score of 85,76%. Based on these results, the SVM method demonstrates superior overall performance compared to Random Forest in classifying sentiment of Gojek user reviews.]]>
Copyrights © 2026
