Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Journal of Engineering and Scientific Research (JESR)
Wiguna, I Wayan Darma
Unknown Affiliation
Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Engineering Industrial & Manufacturing Engineering

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

Found 1 Documents
Search

 1 
Comparison of SVM & Naïve Bayes Methods in Sentiment Analysis of Electric Vehicle Subsidy Policy Based on X Data Wiguna, I Wayan Darma; Waas, Devi Valentino; Wiguna, I Komang Arya Ganda; Radhitya, Made Leo
Journal of Engineering and Scientific Research Vol. 6 No. 1 (2024)
Publisher : Faculty of Engineering, Universitas Lampung Jl. Soemantri Brojonegoro No.1 Bandar Lampung, Indonesia 35141

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/jesr.v6i1.158

Abstract

The policy of subsidizing electric vehicles has become a widely discussed issue on social media platform X. The provision of electric vehicle subsidies by the Indonesian government aims to stimulate higher adoption of electric vehicles, with the overarching goal of mitigating air pollution. However, the presence of electric vehicle subsidies continues to elicit both support and opposition among the public. On social media platform X, there is a wealth of data suitable for text mining, particularly concerning the current hot topic of electric vehicle subsidies. This research aims to compare the performance of Support Vector Machine (SVM) and Naïve Bayes methods in conducting sentiment analysis on discussions related to the electric vehicle subsidy policy on social media platform X. The testing technique involves using 20% of the total dataset, comprising 5553 data points, and employing 10-fold cross-validation. The results from the 20% test data indicate that the Support Vector Machine (SVM) method's confusion matrix performance is superior, with the highest values achieved using the RBF kernel: accuracy 83.02%, precision 84.61%, and recall 83.02%. In the performance evaluation testing with 10-fold cross-validation, the Support Vector Machine (SVM) method outperforms, especially with the RBF kernel, yielding an average accuracy of 82.88% over 10 iterations.
Co-Authors Radhitya, Made Leo Waas, Devi Valentino Wiguna, I Komang Arya Ganda