Sebastian, Dicky Fernanda
Unknown Affiliation

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

Found 1 Documents
Search

SENTIMENT ANALYSIS OF PUBLIC OPINION ON THE RIGHT OF INQUIRY IN INDONESIA IN 2024 USING THE SUPPORT VECTOR MACHINE (SVM) METHOD Sebastian, Dicky Fernanda; Sulistiani, Heni; Isnain, Auliya Rahman
Jurnal Teknik Informatika (Jutif) Vol. 5 No. 4 (2024): JUTIF Volume 5, Number 4, August 2024
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2024.5.4.1968

Abstract

Research on the right of inquiry refers to public responses on twitter social media related to the 2024 elections. The right of inquiry is a right used in investigations. There are a lot of public opinions about the right of inquiry that are discussed on twitter social media that convey their various opinions or criticisms of government policies towards the 2024 elections. Based on Law No. 17/2014, the right of inquiry of the House of Representatives is regulated in Article 20A of the 1945 Constitution, which regulates the right of inquiry of the House of Representatives. Sentiment analysis is used in this research to determine the accuracy value of public opinion which is categorized into two, namely positive and negative sentiment. In this study, the SVM method is used to identify and find the results of public opinions or responses regarding the issue of the right of inquiry in Indonesia in 2024 which is being widely under the twitter social media platform, so it is necessary to analyze the sentiment. By using the support vector machine (SVM) algorithm and word weighting using TF-IDF (term frequency-inverse document frequency). Data collection using Google Collaboratory tools with the python programming language. The data used were 2,179 tweets with the keywords "inquiry right", "DPR inquiry right", "election inquiry right". The results obtained from the SVM process with an accuracy value of 77%, negative precision value 77%, positive precision value 77%, negative recall value 57%, positive recall value 89%, positive f1-score value 66%, negative f1-score value 82%. The data that has been tested and processed has an adequate accuracy value for SVM algorithm classification using confusion matrix calculation. The results of the research conducted have been effective with the SVM method.