Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal Jurnal Teknik Informatika (JUTIF) Jurnal Algoritma
Ramadani, Romi
Unknown Affiliation
Computer Science & IT

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : Jurnal Algoritma

 1 
Analisis Sentimen pada Ulasan Aplikasi Wondr di Play Store dengan Metode Naïve Bayes Nurhikmah, Suci; Ramadani, Romi; Triyono, Gandung
Jurnal Algoritma Vol 22 No 2 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-2.2507

Abstract

The advancement of digital technology continues to drive innovation in the banking sector, particularly in the development of mobile banking services that are more responsive to customer needs. Bank Negara Indonesia (BNI) has responded to this demand by launching the Wondr application as a replacement for its previous BNI Mobile Banking platform, which has received a wide range of user feedback on the Google Play Store.This study was conducted to understand user opinions and perceptions regarding the Wondr application, with the aim of evaluating feedback that could serve as a strategic basis for enhancing BNI’s digital services. The approach employed sentiment analysis using the Naive Bayes Classifier, implemented in Python. The dataset consisted of 27,124 user reviews.The classification results revealed that 52.9% of the reviews were positive, 39.9% negative, and 7.2% neutral. The Naive Bayes model achieved an accuracy of 82%, although its performance in identifying neutral sentiment remained weak, as evaluated through precision, recall, and F1-Score metrics.These findings indicate that the Wondr application is generally well received by users, although certain aspects still require improvement. The study recommends further exploration of alternative classification algorithms such as Random Forest, Support Vector Machine (SVM), and Deep Learning methodologies, as well as the application of SMOTE techniques to address data imbalance, particularly in neutral sentiment classification.
Co-Authors Deni Mahdiana Nurhikmah, Suci Triyono, Gandung