Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal JURNAL MEDIA INFORMATIKA BUDIDARMA
Danang Bagus Chandra Prasetiyo
Universitas Dian Nuswantoro, Semarang
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering

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

Found 1 Documents
Search

 1 
Metode Naive Bayes Classifier dan Forward Selection Untuk Deteksi Berita Hoaks Bahasa Indonesia Danang Bagus Chandra Prasetiyo; Pulung Nurtantio Andono; Catur Supriyanto
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 7, No 3 (2023): Juli 2023
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v7i3.6459

Abstract

Presently, hoaxes or fake news have become a serious threat to human life. Hoax news can not only cause material harm and chaos in society, but now fake news can also affect a person's psychology by causing fear and terror, and at worst, it can break national sovereignty. To process the classification, data miming is used so that it can be seen whether a news item is hoax or genuine news. In this study, researchers used naïve Bayes as a classification method. Then the researcher also uses the forward selection function used in the Naïve-Bayes method. Forward selection is the best regression model formation method based on an approach by selecting variables by including the independent variables that have the largest correlation values. While the naïve Bayes algorithm works conditionally independent between predictions. Based on the tests that have been carried out on the classification of Indonesian hoaxes using Naïve Bayes and Forward Selection to obtain an accuracy of 84%, and a recall of 63.72% while the precision increases to 91.19% with an increase in accuracy of 8.8% and a recall of 8.19% and precision increased by 20.98%. It is hoped that the level of accuracy in the classification of Indonesian hoax news using the naïve Bayes method using forward selection can be increased.
Co-Authors Catur Supriyanto Pulung Nurtantio Andono