Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Fahma : Jurnal Informatika Komputer, Bisnis dan Manajemen
Igo Fiqi Nurwahid
STMIK EL RAHMA Yogyakarta
Computer Science & IT Decision Sciences, Operations Research & Management Engineering

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

Found 1 Documents
Search

 1 
Perbandingan Naïve Bayes dan Support Vector Machine pada Klasifikasi Sentimen Tokopedia Di Playstore Igo Fiqi Nurwahid; Untung Subagyo
Jurnal Informatika Komputer, Bisnis dan Manajemen Vol 24 No 3 (2026): September 2026
Publisher : LPPM STMIK El Rahma Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61805/fahma.v24i3.230

Abstract

Tokopedia is one of the largest e-commerce platforms in Indonesia, generating a growing number of user reviews that makes manual sentiment analysis inefficient. This study compares the performance of Naïve Bayes and Support Vector Machine (SVM) in classifying sentiment in Tokopedia application reviews. Data were collected using the google-play-scraper library and automatically labeled based on user ratings, with ratings of 1–2 classified as negative and 4–5 as positive. After preprocessing, including case folding, cleaning, tokenization, stopword removal, and stemming using Sastrawi, 1,212 reviews were obtained, comprising 609 negative and 603 positive reviews. Text features were extracted using TF-IDF, and the models were evaluated using 5-fold cross-validation. With default parameters, Naïve Bayes and SVM achieved accuracies of 75.99% and 74.83%, respectively. After GridSearchCV tuning, Naïve Bayes achieved 76.65% accuracy and 73.28% F1-score, while SVM achieved 77.81% accuracy and 76.51% F1-score. These results show that hyperparameter tuning affects model comparison, with tuned SVM slightly outperforming Naïve Bayes.
Co-Authors Untung Subagyo