<![CDATA[The growth of information technology has driven the widespread use of online shopping applications, including Alfagift, the official app of Alfamart. User reviews of this application on the Google Play Store reflect their perceptions and satisfaction, which, when analyzed correctly, can provide important insights for app developers. This study aims to classify the sentiment of user reviews on the Alfagift app using the Support Vector Machine (SVM) method optimized by the Particle Swarm Optimization (PSO) algorithm. SVM is a widely used algorithm due to its accuracy in classification. To achieve optimal performance, SVM parameters need to be carefully tuned, and Particle Swarm Optimization (PSO) is used as an effective method for this optimization. The data used in this study were obtained from Google Play Store through web scraping using the google-play-scraper library. The initial classification result using SVM without optimization produced an accuracy of 87.25%. After parameter optimization using the PSO algorithm, the accuracy increased to 90.41%. These findings show that the use of PSO significantly improves the performance of sentiment classification models for user reviews. Therefore, the combination of SVM and PSO methods is effective for analyzing user sentiment in the Alfagift app for evaluation and future development purposes.]]>
Copyrights © 2025
