Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Paradigma
Kasbi, Hazwan Arif Bin
Unknown Affiliation
Computer Science & IT

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

Found 1 Documents
Search

 1 
Sentiment Analysis of Mimo Application Reviews Using the Naive Bayes Algorithm to Support Digital Learning Transformation Sugiharto, Prasetyawan Aji; Ardiansyah, Angga; Agustina, Candra; Wasiyanti, Sri; Saputra, Rizal Amegia; Saefudin, Dede Firmansyah; Kasbi, Hazwan Arif Bin
Paradigma - Jurnal Komputer dan Informatika Vol. 28 No. 2 (2026): September 2026 Period
Publisher : LPPM Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/p.v28i2.14394

Abstract

The rapid growth of mobile-based educational platforms requires continuous evaluation of user satisfaction to drive digital learning transformation. This study aims to analyze user sentiments toward the Mimo application based on Google Play Store reviews using the Naive Bayes algorithm. The research dataset consists of 290 balanced reviews categorized equally into positive and negative classes (145 reviews each). The methodology encompasses systematic text preprocessing—including case folding, regular expression cleaning, stopword removal, and stemming using the Sastrawi library—followed by TF-IDF feature extraction and classification modeling via Multinomial Naive Bayes. Model validation was conducted utilizing Stratified 5-Fold Cross-Validation and an 80:20 hold-out test split. The evaluation results demonstrate that the Naive Bayes model achieves a high average accuracy of 80.00% (1.38%) with an overall hold-out test accuracy of 82.76%, a macro precision of 87.18%, and a macro F1-score of 82.23%. These findings indicate that the model provides robust and stable classification performance. Furthermore, this study delivers strategic insights for developers of gamified mobile learning applications, demonstrating that data-driven user feedback analysis serves as a vital foundation to accelerate the transformation of adaptive, learner-centric digital education
Co-Authors Angga Ardiansyah Candra Agustina Dede Firmansyah Saefudin Prasetyawan Aji Sugiharto Rizal Amegia Saputra Sri Wasiyanti, Sri