Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Jurnal Teknologi Dan Sistem Informasi Bisnis
Ferry Gunawan Wijaya Kusuma
Sistem Informasi, Teknik, Universitas Muria Kudus

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

Found 1 Documents
Search

 1 
Analisis Sentimen Ulasan Produk E-Commerce Menggunakan Metode Support Vector Machine (SVM) Zukhrufana Firdausy Nuzula; Ferry Gunawan Wijaya Kusuma; Muhammad Arifin
Jurnal Teknologi Dan Sistem Informasi Bisnis Vol. 8 No. 3 (2026): Juli 2026
Publisher :  Prodi Sistem Informasi Universitas Dharma Andalas

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47233/jteksis.v8i3.14

Abstract

The rapid growth of e-commerce platforms in Indonesia, including Shopee, Tokopedia, and Lazada, has led to a significant increase in user reviews. These reviews contain valuable insights for developers to improve service quality; however, their large volume makes manual analysis impractical, necessitating an automated artificial intelligence-based approach. This study aims to develop a sentiment analysis system for user reviews from the three largest e-commerce platforms in Indonesia using the Support Vector Machine (SVM) method. A total of 1,000 reviews per application were collected from the Google Play Store using web scraping techniques. The preprocessing stage included text cleaning, URL and symbol removal, and space normalization. Sentiment labeling was performed based on user ratings: ratings of 4–5 as positive, 3 as neutral, and 1–2 as negative. Text features were extracted using the TF-IDF approach, and the model was trained using an SVM with a linear kernel. The results show that the model achieved an average accuracy of 87.4%, outperforming Naive Bayes and Random Forest methods. Sentiment distribution revealed a dominance of positive sentiment across all three platforms (average 70.4%), with Shopee recording the highest positive rate (72.8%) and Lazada showing the highest negative sentiment (18.4%). The TF-IDF-based SVM approach proves highly effective for sentiment analysis of Indonesian-language text in the e-commerce domain.
Co-Authors Muhammad Arifin Zukhrufana Firdausy Nuzula