Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Abel Filemon Haganta Kaban
Fakultas Ilmu Komputer, Universitas Brawijaya
Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Analisis Sentimen Aplikasi E-Goverment berdasarkan Ulasan Pengguna menggunakan Metode Maximum Entropy dan Seleksi Fitur Mutual Information Abel Filemon Haganta Kaban; Indriati Indriati; Novanto Yudistira
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 5 No 4 (2021): April 2021
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

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%.
Co-Authors Indriati Indriati Novanto Yudistira