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.
The development of technology also influences changes in campaign patterns. Campaign activities are part of the process of Election of Regional Heads. The aim of the campaign is to mobilize public participation, which is carried out directly or through social media. Social media becomes a channel for interaction between candidates and their supporters. Interactions that occur during the campaign period can be one indicator of the success of the closeness between voters and candidates. This study aims to get the pattern of campaign interactions that occur on Twitter social media channels. This interaction pattern is classified as a model in measuring the success of campaigns on social media. The research begins with obtaining data through the data retrieval process using the API feature provided by Twitter. Furthermore, pre-processing is carried out before data can be processed in an algorithmic method. This stage is done to improve data quality so as to improve accuracy. Naive Bayes Classifier was chosen because of a simple procedure, then Kernel Estimator (KE) was used to improve performance. The use of naive Bayes Kernel Estimator can improve model performance from 76.74% to 80.14%. Testing models with split percentage methods on several combinations get satisfactory results.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.