GROUPING OF JKN MOBILE USER COMMENTS USING THE K-MEDOIDS METHOD

Abstract

The JKN Mobile application has become one of the essential platforms used by the public to access healthcare services in Indonesia. As the number of users continues to grow, the feedback and comments provided by users have become increasingly diverse. Analyzing these comments is crucial for identifying common issues faced by users, understanding their needs, and improving the quality of the application’s services. This study aims to cluster user comments on the JKN Mobile application using the K-Medoids method. The clustering process begins with cleaning and preprocessing the text data to prepare it for analysis. Subsequently, the K-Medoids algorithm is applied, with the optimal number of clusters determined using the Elbow method. The clustering results reveal several groups of comments, such as positive feedback on the application, requests for additional features, and suggestions for service improvements. This research is expected to assist JKN Mobile application managers in better understanding user needs and complaints, thereby enabling more targeted service enhancements. The implementation of comment clustering provides valuable insights for the development of a more responsive and user-centric application.