Journal of Computer System and Informatics (JoSYC)
Vol 5 No 3 (2024): May 2024

Analisis Sentimen Media Sosial Twitter Terhadap Calon Presiden RI Tahun 2024 Menggunakan Klasifikasi Algoritma Naïve Bayes

Effendi, Muhammad Makmun (Unknown)
Zy, Ahmad Turmudi (Unknown)
Arwan, Asep (Unknown)



Article Info

Publish Date
31 May 2024

Abstract

The progress of social media is currently being felt by many Indonesian people, one of the social media that is often used is Twitter, which is a media for posting information. Currently the viral post is the election of Presidential Candidates (capres) of the Republic of Indonesia which will be held in 2024, in line with this, the General Election Commission (KPU) is holding a presidential candidate debate which will be held on various television media in Indonesia and from the results of this debate the Indonesian people usually give opinions or comments on the debate from the positive and negative sides of the presidential candidates who appeared at that time, namely Anis, Prabowo and Ganjar Pranowo. To find out the results of sentiment towards the presidential candidates, the researchers carried out an analysis using a classification of tweets containing public sentiment towards the 2024 presidential candidacy, namely Anis, Prabowo and Ganjar with the classification method used in this research is Naive Bayes Classification (NBC). Anies Baswedan dataset 61.35% of Twitter users have negative comments and 39.65% of Twitter users have positive comments, Ganjar Pranowo dataset 59.12% of Twitter users have negative comments and 41.88% of Twitter users have positive comments, Ganjar Prabowo Subianto dataset 49.25% Twitter users commented negatively and 51.75% of Twitter users commented positively. Comparing the results of the three presidential candidates, Anies Baswedan's accuracy value is smaller than the other two candidates because Anies Baswedan has more negative comments than the other two candidates. Anies Baswedan got an accuracy value of 67.23%, Prabowo Subianto 83.42% and Ganjar Pranowo 88.15%. The amount of data affects the results of sentiment analysis, the more data the better the accuracy value obtained.

Copyrights © 2024






Journal Info

Abbrev

josyc

Publisher

Subject

Computer Science & IT Decision Sciences, Operations Research & Management Industrial & Manufacturing Engineering

Description

Journal of Computer System and Informatics (JoSYC) covers the whole spectrum of Artificial Inteligent, Computer System, Informatics Technique which includes, but is not limited to: Soft Computing, Distributed Intelligent Systems, Database Management and Information Retrieval, Evolutionary ...