Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Jurnal Teknik Informatika (JUTIF)
Rice Novita
Information Systems Study Program, Faculty of Science and Technology, UIN Suska Riau, Indonesia
Computer Science & IT

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

Found 1 Documents
Search

 1 
SENTIMENT ANALYSIS OF COMMENTS ON GOOGLE PLAY STORE, TWITTER AND YOUTUBE TO THE MYPERTAMINA APPLICATION WITH SUPPORT VECTOR MACHINE Aji Nursalim; Rice Novita
Jurnal Teknik Informatika (Jutif) Vol. 4 No. 6 (2023): JUTIF Volume 4, Number 6, Desember 2023
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2023.4.6.1059

Abstract

Application is an important requirement in a business because it makes work more efficient thereby increasing the results of the company, pertamina as a supplier of fuel oil (BBM) in Indonesia provides the latest innovations by launching the mypertamina application for purchasing BBM which raises public opinion, and conveys its aspirations in social media. Text mining is a way to group community comments because text mining has an analysis that focuses on analyzing a comment that is extracted into information. The purpose of this study was to determine public sentiment towards the use of mypertamina by classifying comments using the Support Vector Machine (SVM) algorithm and finding the best kernel among linear, polynomial and RBF. In this study, data was taken from three social media, namely Google Play Store with 18.000 data, Twitter with 20.000 data and YouTube with 6.400 data with a total of 44.400 data. Sentiment is carried out by giving positive and negative classes, the accuracy obtained from sentiment is carried out for Google Play Store data of 95%, Twitter 76% and YouTube 99% and it is known that the best svm kernel in this study is the RBF kernel which outperforms the linear and polynomial kernels.
Co-Authors Aji Nursalim