Analisis Sentimen Pengguna Aplikasi Mobile JKN melalui Ulasan Google Play Store Menggunakan Metode SVM
Abstract
The JKN Mobile application, launched by BPJS Kesehatan in 2017, aims to facilitate participants' access to healthcare services. However, its implementation presents various challenges for users, and understanding the large number of reviews is challenging due to the numerous steps involved. This study aims to analyze the sentiment of JKN Mobile application users' reviews on the Google Play Store. Review data was collected from November 20, 2024, to May 20, 2025, totaling 9,878 reviews. The research steps included data collection, preprocessing, sentiment labeling using TextBlob, classification using SVM, and evaluation using a confusion matrix. The evaluation results showed the model performed well, with an accuracy of 94% (for the newest and most relevant sort data), and precision, recall, and F1-score values above 0.90 for negative, neutral, and positive sentiment. And the main issues that are most frequently reviewed are obtained from the word cloud visualization of the words that most frequently appear in reviews, such as “Application”, “Verification”, “Register”, “Difficult”, and “Easy”.


