Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Jurnal Bumigora Information Technology (BITe)
Rudiyan, Ari
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering

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

Found 1 Documents
Search

 1 
Analisis Sentimen Ulasan Mobile Banking Syariah Berbasis NLPuntuk Evaluasi dan Peningkatan Kualitas Layanan Digital Assani, Moh. Yushi; Rudiyan, Ari; Radiyah, Ummu
Jurnal Bumigora Information Technology (BITe) Vol. 7 No. 2 (2025)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/bite.v7i2.5943

Abstract

Background: The development of Islamic mobile banking services in Indonesia requires improvements in the qualityof digital service management that focuses on user experience. User reviews on application platforms are an importantsource of data for understanding user perceptions, satisfaction, and problems encountered. The use of Natural LanguageProcessing enables systematic and automatic sentiment analysis to support the evaluation of Islamic banking servicequality.Objective: This study aims to analyze the sentiment of user reviews of sharia mobile banking applications and comparethe performance of the Na¨ıve Bayes sentiment analysis model as a classic model and IndoBERT as a transformer-basedmodel.Methods: Data was obtained through web scraping of 1,052 user reviews of the Bank NTB Syariah Mobile Bankingapp from the Google Play Store. Preprocessing steps included case folding, cleaning, stopword removal, stemming, andtokenization. Sentiment labeling was based on user rating scores with three categories: positive, neutral, and negative.Model performance was evaluated using accuracy and F1-score metrics.Result: The test results show that the Na¨ıve Bayes model achieved an accuracy of 78% with an F1-score of 0.74. Meanwhile,the IndoBERT model achieved an accuracy of 88% and an F1-score of 0.86. 
Co-Authors Assani, Moh. Yushi Ummu Radiyah, Ummu