Article Per Year (5 Year)
p-Index From 2020 - 2025
2.504
P-Index
This Author published in this journals
All Journal ComEngApp : Computer Engineering and Applications Journal Bulletin of Electrical Engineering and Informatics Indonesian Journal of Electrical Engineering and Informatics (IJEEI) Annual Research Seminar Sistemasi: Jurnal Sistem Informasi JOURNAL OF APPLIED INFORMATICS AND COMPUTING Indonesian Journal of Electrical Engineering and Computer Science Jurnal Generic JUSTIN (Jurnal Sistem dan Teknologi Informasi)
Dinda Lestarini
Fakultas Ilmu Komputer Universitas Sriwijaya
Computer Science & IT Electrical & Electronics Engineering Engineering

Published : 18 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : JOURNAL OF APPLIED INFORMATICS AND COMPUTING

 1 
Comparison of Support Vector Machine and Random Forest Algorithms in Sentiment Analysis of the JMO Mobile Application Via Mariska, Inneke; Meiriza, Allsela; Lestarini, Dinda
Journal of Applied Informatics and Computing Vol. 9 No. 5 (2025): October 2025
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v9i5.10764

Abstract

JMO Mobile is a digital service application that enables the public to access employment-related information and benefits. User reviews serve as a valuable resource for evaluating service quality, yet systematic sentiment analysis on this application remains limited. This study aims to classify the sentiment of user reviews and compare the performance of Support Vector Machine (SVM) and Random Forest (RF) algorithms. A total of 41,673 reviews were collected through web scraping, then preprocessed through text cleaning, tokenization, stopword removal, stemming, and feature extraction using TF-IDF. The reviews were categorized into positive, negative, and neutral sentiments, and divided into training and testing datasets with an 80:20 ratio. The choice of SVM and RF was based on their proven effectiveness in text classification tasks, with SVM excelling in handling high-dimensional data and RF recognized for its stability in producing reliable results. Model evaluation was conducted using accuracy as the primary metric. The findings indicate that Random Forest achieved an accuracy of 86.15 percent, slightly outperforming SVM at 86.06 percent. While SVM showed superior performance in identifying positive sentiment, Random Forest demonstrated greater consistency across classifications. Overall, Random Forest is considered more suitable for sentiment analysis of public service application reviews. This study contributes an automated approach to understanding user perceptions and offers a reference for selecting classification algorithms in similar cases.
Co-Authors Adelia Azahra Adelia Rizki Putri Ahmad Rifai Ahmad Syakir Muliana Ali Bardadi Allsela Meiriza, Allsela Andesta Angelina Darmawahyuni, Annisa Desty Rodiah Dila Okta Dwi Putri Dinna Yunika Hardiyanti Firdaus Firdaus Firdaus Firdaus Firdaus Firdaus Firdaus Fransiska Prihatini Sihotang, Fransiska Prihatini Hardini Novianti Iriyani, Silfi Kurniawan, Anggy Tias Kurniawan, Anggy Tyas Muhammad Naufal Rachmatullah Muhammad Naufal, Muhammad Pibriana, Desi Rahmadiana, Reva Nur Richa Pratiwi Rizka Dhini Kurnia Rusdy, Taufiqurrahman Sarifah Putri Raflesia Sarifah Putri Raflesia Sarifah Putri Raflesia Sarifah Putri Raflesia, Sarifah Putri Silfi Iriyani Siti Nurmaini Taufiqurrahman Rusdy Taufiqurrahman Taufiqurrahman Via Mariska, Inneke