Article Per Year (5 Year)
p-Index From 2020 - 2025
0.444
P-Index
This Author published in this journals
All Journal Journal of Computer System and Informatics (JoSYC) eCo-Fin
Adelia, Dila
Unknown Affiliation
Computer Science & IT Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Industrial & Manufacturing Engineering

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : Journal of Computer System and Informatics (JoSYC)

 1 
Election Hoax Detection on X using CNN with TF-RF and TF-IDF Weighting Features Adelia, Dila; Astuti, Widi; Lhaksmana, Kemas Muslim
Journal of Computer System and Informatics (JoSYC) Vol 5 No 4 (2024): August 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v5i4.5778

Abstract

X social media is a microblogging platform for sharing brief thoughts and trends. It has become a focal point for expressing political views. The increased political engagement on X social media has facilitated the swift and extensive sharing of ideas. Still, it also brings the risk of spreading false information and hoaxes that can manipulate public opinion. Preventing fake news on social media is crucial because it can influence election outcomes and social stability. For example, X social media has been used during elections to spread hoaxes, such as false claims of vote tampering or misleading information about candidate qualifications. This study implements a Convolutional Neural Network (CNN) due to its advantages in recognizing complex patterns and achieving high performance in tasks like classification. The dataset used in this study consists of 2,670 tweets. The dataset is divided into three subsets: 60% for training, 20% for testing, and 20% for validation. It also uses Term Frequency Relevance Frequency (TF-RF) and Term Frequency Inverse Document Frequency (TF-IDF) weighting features to improve accuracy in detecting fake news. This study compares the TF-RF and TF-IDF weighting features using the CNN classification method on the topic of the 2024 election. The testing results indicate that both TF-RF and TF-IDF achieved similar overall performance, with TF-RF slightly excelling in recall and F1-score. At the same time, TF-IDF showed a marginally higher precision.
Co-Authors Elly, Moh. Iskak Kemas Muslim Lhaksmana Widi Astuti Wilamsari, Feni