Mobile JKN is an e-government application that is used by the government as an innovative use of information and communication technology in government administration. Mobile JKN is an application as part of BPJS Kesehatan's commitment in providing services and easy access for BPJS Kesehatan users. Indonesians can try using the Mobile JKN application and review it on application providers such as the Google Play Store and the App Store. Reviews as a way of expressing opinions, offer data sources in the form of user sentiments regarding the features and services available on the Mobile JKN application. Sentiment analysis research is conducted to analyze the sentiments contained in user reviews by classifying reviews as positive or negative. In this research, Maximum Entropy is used as a classification method with Mutual Information as a feature selection to reduce the number of features used in the classification of user reviews of the Mobile JKN application. In testing, better evaluation results are shown by the use of the Mutual Information feature selection in the classification using Maximum Entropy with an accuracy value obtained of 82.5% compared to without the use of feature selection which results in an accuracy of 79.5%.
Copyrights © 2021