Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Jurnal Repositor
Fatahillah Arsyad
Universitas Muhhammadiyah Malang
Computer Science & IT Engineering

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

Found 1 Documents
Search

 1 
Deteksi Konten Hoax Pada Media Berita Indonesia Menggunakan Multinomial Naïve Bayes Fatahillah Arsyad; Nur Hayatin; Christian Sri Kusuma Aditya
Jurnal Repositor Vol 5 No 4 (2023): November 2022
Publisher : Universitas Muhammadiyah Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22219/repositor.v5i4.1539

Abstract

Hoax news is a problem that needs to be addressed in Indonesia. Launching a report from Kominfo (Ministry of Communication and Information) in 2020 alone there were 3464 hoax news detected. considering the large number, it will be very difficult to identify every news that is in Indonesia, not quickly let alone comprehensively. Therefore, it takes a tool or system that can detect the news that is spread, quickly and efficiently. With this purpose, this research was carried out, using the method used by Multinomial Naïve Bayes (MNB). In previous studies, there are still some shortcomings that can be covered by improvisation. To improvise in the classification of hoax news, the MNB method was chosen for this study. MNB itself is a type of Naïve Bayes which is often used for text analysis where data is represented in the form of a word frequency vector. as a comparison rival for MNB, Gaussian Naïve Bayes will also be brought in for this research. with a total of 994 news data sourced from turnbackhoax.id and as a comparison this study also uses data from previous research which amounted to 250 news. The results obtained by the GNB method reach 94% accuracy and the highest accuracy for the MNB method is 96% which shows MNB is better.
Co-Authors Christian Sri Kusuma Aditya Nur Hayatin