Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal JOURNAL OF INFORMATION SYSTEM RESEARCH (JOSH)
Vivi Andriani
Universitas Muhammadiyah Prof. Dr. Hamka, Jakarta
Computer Science & IT Decision Sciences, Operations Research & Management

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

Found 1 Documents
Search

 1 
Analisis Sentiment Ulasan Aplikasi Riliv di Google Playstore dengan Algoritma SVM Vivi Andriani; Firman Noor Hasan
Journal of Information System Research (JOSH) Vol 6 No 4 (2025): July 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v6i4.7860

Abstract

This study aims to conduct sentiment analysis on user reviews of the Riliv: Mental Health App on Google Play Store using the Support Vector Machine (SVM) algorithm. The analysis process includes review data collection via web scraping, text cleaning using text preprocessing, automatic labeling based on rating scores, data transformation using the TF-IDF method, data splitting with Stratified K-Fold Cross Validation, SVM model training, and performance evaluation. The dataset comprises 2,000 reviews with an imbalanced label distribution: positive (75,3%), netral (5,3%), and negative (19,4%). The classification results show that the SVM model achieved an accuracy of 85.56%. It performed well in identifying positive sentiment with an f1-score of 0.96 and negative sentiment with 0.69. However, the model failed to classify neutral sentiment due to the small number of data, which was insufficient for meaningful pattern recognition. Evaluation and visualization results indicate that label imbalance is a major challenge. Therefore, additional strategies such as data balancing, class weighting, or the use of alternative algorithms are necessary. This research is expected to serve as a foundation for developing a more accurate and fair sentiment analysis system across all sentiment categories in the context of digital mental health services.
Co-Authors Firman Noor Hasan