Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Jurnal Teknik Informatika (JUTIF)
Harahap, Jasmine Avrile Kaniasari
Unknown Affiliation
Computer Science & IT

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

Found 1 Documents
Search

 1 
ANALYSIS AND IMPLEMENTATION OF SENTIMENT SYSTEM ON THE ELECTABILITY OF INDONESIAN PRESIDENTIAL CANDIDATES 2024 USING SUPPORT VECTOR MACHINE METHOD Harahap, Jasmine Avrile Kaniasari; Syaifullah JS, Wahyu; Idhom, Mohammad
Jurnal Teknik Informatika (Jutif) Vol. 5 No. 4 (2024): JUTIF Volume 5, Number 4, August 2024 - SENIKO
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2024.5.4.2029

Abstract

Indonesia is a country that implements democracy in choosing presidential candidates through the election process. People have their own views on the presidential candidates they support, and in this digital era, social media is the main platform for people to express their opinions. Public opinion can be positive or negative, public opinion, hate speech, and various other comments that can cause hostility, insults, debates, and disputes. In this study, data modeling using the Support Vector Machine (SVM) method will be evaluated using a confusion matrix. The data used for anies data is 1607 tweets, prabowo data is 1761 tweets, and ganjar data is 1607 tweets with the keywords “anies baswedan”, “prabowo subianto”, and “ganjar pranowo” with the data collection period from November - December 2023. The results of this study show that the sentiment classification model has good performance. For Anies Baswedan data, the SVM model achieved accuracy of 86.64%, precision of 86.69%, recall of 86.64%, and f1-score of 86.62%. For Prabowo Subianto data, the model achieved an accuracy of 90.65%, precision of 90.81%, recall of 90.65%, and f1-score of 90.61%. Meanwhile, for Ganjar Pranowo data, the model achieved an accuracy of 93.78%, precision of 93.67%, recall of 93.78%, and f1-score of 93.72%. These results show that the system is able to classify people's sentiment.
Co-Authors idhom, Mohammad Syaifullah JS, Wahyu