Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal JURIKOM (Jurnal Riset Komputer)
Diah Fitriani
Universitas Nahdlatul Ulama Sunan Giri, Bojonegoro
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering

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

Found 1 Documents
Search

 1 
Studi Komparatif Algoritma Random Forest dan Logistic Regression dalam Analisis Sentimen Ulasan Aplikasi E-Wallet Dana Diah Fitriani; Afril Efan Pajri; Aprillia Dwi Ardianti
JURIKOM (Jurnal Riset Komputer) Vol. 13 No. 1 (2026): Februari 2026
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/jurikom.v13i1.9517

Abstract

The increasing use of digital wallets in Indonesia has led to a growing number of user opinions expressed, including on the DANA platform in the Play Store. These reviews reflect users' experiences and satisfaction levels, necessitating sentiment analysis to comprehend public opinions about the application’s service quality. The study conducts an analytical comparison between Random Forest and Logistic Regression methods in classification sentiments for DANA application. Data was obtained through scraping techniques, resulting in 2,068 reviews after the cleaning process. The analysis stages include text preprocessing, labeling based on review scores, weighting using TF-IDF, and modeling with both algorithms. The evaluation results demonstrate that Random Forest obtains an accuracy of 86.23%, while Logistic Regression obtains an accuracy of 84.54%. Both models are capable of classifying positive sentiments well but are less optimal in detecting negative sentiments. Random Forest shows higher performance compared to Logistic Regression within the task in sentiment analysis for DANA app reviews. Thus, we can conclude that using the random forest algorithm is able to produce accurate sentiment analysis and can act as a basis for making decisions in further research
Co-Authors Afril Efan Pajri Aprillia Dwi Ardianti