Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Jurnal Algoritma
Anadya Nisrina Salsabila
Universitas Sriwijaya
Computer Science & IT

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

Found 1 Documents
Search

 1 
Analisis Sentimen Ulasan Pengguna Pada Aplikasi M2U ID Menggunakan Metode Random Forest dan Support Vector Machine (SVM) Anadya Nisrina Salsabila; M. Rudi Sanjaya; Ali Ibrahim; Endang Lestari Ruskan
Jurnal Algoritma Vol 23 No 1 (2026): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.23-1.3375

Abstract

The M2U ID app is the primary digital banking platform of PT Bank Maybank Indonesia Tbk, serving as a crucial tool for supporting customers’ online transactions. The objective of this study is to analyze user review sentiment on the Google Play Store by comparing the performance of the Random Forest and Support Vector Machine (SVM) algorithms. A total of 16,270 review data points were collected via web scraping and processed through preprocessing stages and feature extraction using N-Gram-based TF-IDF with Chi-Square feature selection using the SelectKBest approach. Given the significant imbalance in data distribution, this study applied class weighting techniques as well as hyperparameter optimization using Grid Search and 5-Fold Cross-Validation. Testing on 3,254 test data points indicated that SVM performed more optimally with an accuracy rate of 82% and an F1-Macro score of 0.6344, compared to Random Forest, which yielded an accuracy of 73% and an F1-Macro score of 0.5832. The main contribution of this study is an in-depth analysis of classification errors in the minority (neutral) class, which has a low F1-score (0.16–0.17). The results of the error analysis show that the model’s limitations are caused by the ambiguity of technical features and the overlap of vocabulary in reviews with minimal emotional content.
Co-Authors Ali Ibrahim Endang Lestari Ruskan M. Rudi Sanjaya