Levels of Political Participation Based on Naive Bayes Classifier

IJCCS (Indonesian Journal of Computing and Cybernetics Systems). 2019;13(1):73-82 DOI 10.22146/ijccs.42531


Journal Homepage

Journal Title: IJCCS (Indonesian Journal of Computing and Cybernetics Systems)

ISSN: 1978-1520 (Print); 2460-7258 (Online)

Publisher: Universitas Gadjah Mada

Society/Institution: Universitas Gadjah Mada, Departemen Ilmu Komputer, Elektronika dan Instrumensai

LCC Subject Category: Science: Science (General): Cybernetics | Science: Mathematics: Instruments and machines: Electronic computers. Computer science

Country of publisher: Indonesia

Language of fulltext: Indonesian, English

Full-text formats available: PDF



Rumaisah Hidayatillah (Department of Informatics Engineering, Universitas Narotama, Surabaya)

Mirwan Mirwan (Department of Informatics Engineering, Universitas Narotama, Surabaya)

Mohammad Hakam (Department of Computer Systems, Universitas Narotama, Surabaya)

Aryo Nugroho (Faculty of Computer Science, Universitas Narotama, Surabaya, Indonesia)


Blind peer review

Editorial Board

Instructions for authors

Time From Submission to Publication: 12 weeks


Abstract | Full Text

Nowadays, social media is growing rapidly and globally until it finally became an important part of society. During campaign period for the regional head election in Indonesia, the candidates and their supporting parties actively use social media as a campaign tool. Social media like Twitter has been known as a political microblogging media that can provide data about current political event based on users’ tweets. By using Twitter as a data source, this study analyzes public participation during campaign period for 2018 Central Java regional head election. The purpose is to observe how much reaction is given to each candidate who advanced in the election. By using the crawling program, all tweets containing certain candidate names will be downloaded. After going through a series of preprocessing stages, data can be classified using Naive Bayes. Predictor features in classification datasets are the number of replies, retweets, and likes. While the target variable is reaction that is divided into three levels, including high, medium, and low. These levels are determined based on users’ reaction in a tweet. By using these rules, Naive Bayes managed to classify data correctly as much as 76.74% for Ganjar Pranowo and 68.81% for Sudirman Said.