Article Per Year (5 Year)
p-Index From 2020 - 2025
0.408
P-Index
This Author published in this journals
All Journal Jurnal Ekonomi Manajemen Sistem Informasi Jurnal Indonesia : Manajemen Informatika dan Komunikasi
Arisenja, Ni Luh Bumi
Unknown Affiliation
Computer Science & IT Economics, Econometrics & Finance Languange, Linguistic, Communication & Media Library & Information Science

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : Jurnal Indonesia : Manajemen Informatika dan Komunikasi

 1 
Analisis Sentimen Pemecatan Shin Tae-yong pada Media Sosial X untuk Monitoring Opini Publik Menggunakan Naïve Bayes dan Support Vector Machines Arisenja, Ni Luh Bumi; Mulyana, Dadang Iskandar
Jurnal Indonesia : Manajemen Informatika dan Komunikasi Vol. 6 No. 3 (2025): September
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat (LPPM) STMIK Indonesia Banda Aceh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63447/jimik.v6i3.1561

Abstract

Social media has become a primary platform for people to voice their opinions on national issues, including in the field of sports. One of the hotly discussed issues is the dismissal of the Indonesian National Team coach, Shin Tae-Yong. This study aims to analyze public sentiment towards the dismissal through social media platform X (formerly known as Twitter) using two machine learning algorithms, namely Naïve Bayes and Support Vector Machines (SVM). Data was obtained through a crawling process using the keyword pecat shin tae-yong, then carried out pre-processing stages such as cleaning, tokenizing, stopword removal, and stemming. The evaluation process was carried out using a confusion matrix to measure accuracy, precision, recall, and F1-score. The classification results show that the Naïve Bayes model produces an accuracy of 92.91%, while the positive precision value is 81.33%, and the negative precision is 100%. Meanwhile, the SVM (Support Vector Machine) model provided more optimal results with an accuracy of 97.97%, a positive precision of 96.72%, a negative precision of 98.53%, and a positive recall of 96.72% and a negative recall of 98.53%. Based on these results, it can be concluded that the SVM algorithm performed better in analyzing public opinion regarding the coach's dismissal issue. This research is expected to contribute as a reference data-based public opinion monitoring system for more transparent public policymaking.
Co-Authors Alafia, Evi Alfarisy, Salman Dadang Iskandar Mulyana`