Sentiment Analysis on Twitter Using Naïve Bayes and Logistic Regression for the 2024 Presidential Election

Mantika, Alisya Mutia (2024) Sentiment Analysis on Twitter Using Naïve Bayes and Logistic Regression for the 2024 Presidential Election. Journal blockchain, NFTs and metaverse tecnology, 2 (1). pp. 44-55. ISSN 30309832

[img] Text
116
Download (3kB)

Abstract

In accordance with the notion of democracy which is the basis of the state of Indonesia, general elections will be held in 2024. In the implementation of the General Election there is a campaign to lead the public vote to choose the best candidate according to public opinion. Twitter social media is one of the media to voice opinions as well as share information to become one of the indirect campaigning platforms. Social media also does not escape negative issues, community rumors, and even the digital footprint of presidential candidates which can be a very important consideration in campaigning. This research aims to see the public's response to the 2024 presidential candidates. This research is conducted based on public opinion on presidential candidates, then public opinion data taken from Twitter social media will go through a pre-processing process to clean the data before the data is classified into Naive Bayes and Linear Regression modeling. The two classification models are then sought for the highest performance accuracy value and confusion matrix with 80:20 splitting data. The results showed that the Naive Bayes classification model had a higher accuracy value than the Logistic Regression classification model, which was 63% for Anies Baswedan candidate, 77% for Ganjar Pranowo candidate, and 44% for Prabowo Subianto. The highest accuracy value was obtained by the sentiment data of 2024 presidential candidate Ganjar Pranowo, which was 77%.

Item Type: Article
Subjects: T Technology > T Technology (General)
Z Bibliography. Library Science. Information Resources > Z665 Library Science. Information Science
Divisions: Artikel > Informatika dan Sistem Informasi
Depositing User: Miss Rahma Rahmawati
Date Deposited: 15 May 2024 07:07
Last Modified: 15 May 2024 07:07
URI: http://repository.unas.ac.id/id/eprint/10961

Actions (login required)

View Item View Item
Unas Repository is powered by EPrints 3 which is developed by the School of Electronics and Computer Science at the University of Southampton. More information and software credits.