Mobile JKN is a digital healthcare application developed by BPJS Kesehatan to facilitate public access to healthcare services. User reviews on Google Play Store provide valuable feedback for evaluating service quality. This study aims to analyze user sentiment and identify the main topics discussed in Mobile JKN reviews using Support Vector Machine (SVM) and Latent Dirichlet Allocation (LDA). Reviews were collected through web scraping and processed using filtering, sentiment labeling, and text preprocessing. SVM was employed for sentiment classification, while LDA was applied to negative reviews for topic modeling. The SVM model achieved an accuracy of 96% with an average 5-fold cross-validation accuracy of 95.19%. Topic modeling identified three major issues: authentication and account management, online queue and healthcare referral services, and application stability with digital administrative services. These findings provide useful insights for improving Mobile JKN service quality and user experience.
Copyrights © 2026