Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal SAINTEK
Endrik
Unknown Affiliation
Automotive Engineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Engineering Industrial & Manufacturing Engineering

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

Found 1 Documents
Search

 1 
Analisis Sentimen Masyarakat Mengenai Kandidat Calon Presiden 2024 Dari Media Sosial Twitter Menggunakan Metode Naive Bayes Dan Feature Selection Particle Swarm Optimization Asep Arwan Sulaeman; Endrik
Prosiding Sains dan Teknologi Vol. 4 No. 1 (2025): Seminar Nasional Sains dan Teknologi (SAINTEK) ke 4 - Februari 2025
Publisher : DPPM Universitas Pelita Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

The 2024 Indonesian presidential election represents the realization of people’s sovereignty in selecting leaders who are aspirational, qualified, and responsible for public welfare. Public opinion plays a crucial role in shaping the popularity of each candidate, especially through social media platforms such as Twitter. The large volume of opinions shared online provides valuable data for analyzing public sentiment toward the top three presidential candidates in 2024. This study aims to analyze public sentiment regarding Anies Baswedan, Ganjar Pranowo, and Prabowo Subianto using the Naïve Bayes method combined with Feature Selection Particle Swarm Optimization (PSO) to improve classification performance. The evaluation metrics used in this research are Accuracy, Precision, and Recall to measure the effectiveness of the sentiment classification model. The results show varying performance across the three datasets. For Anies Baswedan, the model achieved an accuracy of 63.02%, recall of 65.13%, and precision of 64.61%. For Ganjar Pranowo, the highest performance was obtained with an accuracy of 87.14%, recall of 87.46%, and precision of 85.43%. Meanwhile, Prabowo Subianto’s dataset resulted in an accuracy of 83.17%, recall of 83.17%, and precision of 84.17%. Overall, the method demonstrated the best performance on Ganjar Pranowo’s dataset.
Co-Authors Asep Arwan Sulaeman