Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Journal of Big Data Analytic and Artificial Intelligence
Aura Kristiani Pongamba
Prodi Sistem Informasi, STMIK PPKIA Tarakanita Rahmawati
Computer Science & IT

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

Found 1 Documents
Search

 1 
Aplikasi Analisis Sentimen Ulasan Chatgpt pada Google Play Menggunakan Metode Naïve Bayes Munirah Munirah; Aura Kristiani Pongamba; Suprianto Suprianto; Lies Hartono
Journal of Big Data Analytic and Artificial Intelligence Vol 9 No 1 (2026): JBIDAI Juni 2026
Publisher : STMIK PPKIA Tarakanita Rahmawati

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.71302/jbidai.v9i1.93

Abstract

The rapid development of artificial intelligence technology has led to increased use of the ChatGPT application on the Google Play Store, generating a wide range of user reviews with positive, neutral, and negative sentiments. These reviews serve as an important source of information to measure user satisfaction and evaluate service quality; however, the large volume of data makes manual analysis inefficient and time-consuming. This study aims to analyze user review sentiments and develop a web-based automatic classification system using the Naïve Bayes method. The dataset consists of 300 Indonesian-language reviews collected through Google Play Scraper during the period of August–September 2025. The data were processed through several preprocessing stages, including case folding, tokenizing, normalization, stopword removal, and stemming. Furthermore, TF-IDF weighting, data splitting into training and testing sets, and evaluation using a confusion matrix were conducted. The results show that out of 10 test data, 7 were correctly classified while 3 were misclassified, resulting in an accuracy of 70%. Further evaluation indicates that the negative class achieved the best performance with 100% recall, 83% precision, and an F1-score of 91%, while the neutral and positive classes showed lower performance, particularly in precision and recall values. Therefore, the Naïve Bayes method is considered sufficiently effective for classifying user review sentiments and can be utilized as a basis for evaluating and improving the quality of application services.
Co-Authors Lies Hartono Munirah Munirah Suprianto Suprianto