Article Per Year (5 Year)
p-Index From 2019 - 2024
0.23
P-Index
This Author published in this journals
All Journal INFOKUM
Rahmi Aulia Barlian
Unknown Affiliation
Computer Science & IT

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

Found 1 Documents
Search

 1 
Influence of Demographics for Prediction of Election Participation Using Logistic Regression Algorithm Rahmi Aulia Barlian; Arif Senja Fitrani; Metatia Intan Mauliana
INFOKUM Vol. 10 No. 03 (2022): August, Data Mining, Image Processing, and artificial intelligence
Publisher : Sean Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (325.926 KB)

Abstract

Indonesia is a democratic country for General Elections (Election) which are carried out directly, freely, confidentially, honestly, and fairly. Several stages of the election, among others, begin with compiling a permanent voter list (DPT), determination of polling stations (TPS), and recapitulating election results. Various factors, including the demographic factor, can affect citizen participation in the general election. Demographic data covers Energy, Geographic, Education, Health, Population, Economy, Communication, and Transportation factors. This study tries to combine election data with demographic data taken from the official website of the Central Statistics Agency (BPS) of Mojokerto Regency and data on the results of the 2019 Election calculations taken from the official website of the General Election Commission (KPU) of Mojokerto Regency. Preprocessing steps are data cleaning, data integration, and correlation attributes for a more optimal presentation of the dataset and the distribution of four split datasets (training data and testing data) to find the best results. Implementation of classification method with Logistic Regression (LR) algorithm to predict community participation at the TPS level. From the test results of four split datasets, the highest predictive value was 64.80% in composition 3 with a ratio of 80:20, where 127 data were labeled low, and 291 data were labeled high.
Co-Authors Arif Senja Fitrani Mauliana, Metatia Intan