Language-Independent Features for Detecting Fake News: A Case Study of COVID-19 Twitter News Feed

W. K. Wong; Jeffery T.H. Kong; Filbert H. Juwono; Regina Reine

doi:10.1049/icp.2023.1755

Language-Independent Features for Detecting Fake News: A Case Study of COVID-19 Twitter News Feed

W. K. Wong, Jeffery T.H. Kong, Filbert H. Juwono, Regina Reine

Department of Electrical and Electronic Engineering

Research output: Contribution to journal › Conference article › peer-review

1 Citation (Scopus)

Abstract

Social media platforms allow users to create and share information instantly. Due to the large amount of information on the social media platforms, some users may not be able to identify fake news. Fake news may be in a form of misinformation or disinformation and can lead to the loss of public trust on certain issues. It is crucial for social media users to detect the presence of fake news efficiently and in a timely manner. This paper aims to investigate the effectiveness of Support Vector Machine (SVM) classification approach to detect Twitter fake news. It is shown that SVM with linear kernel results in good accuracy of around 84% on independent test dataset. Furthermore, linear kernel function outperforms non-linear and polynomial kernel functions.

Original language	English
Pages (from-to)	12-17
Number of pages	6
Journal	IET Conference Proceedings
Volume	2023
Issue number	11
DOIs	https://doi.org/10.1049/icp.2023.1755
Publication status	Published - 2023
Event	2023 International Conference on Green Energy, Computing and Intelligent Technology, GEn-CITy 2023 - Hybrid, Iskandar Puteri, Malaysia Duration: 10 Jul 2023 → 12 Jul 2023

Access to Document

10.1049/icp.2023.1755

Cite this

@article{28b69d54366347b0a1db007345155d50,

title = "Language-Independent Features for Detecting Fake News: A Case Study of COVID-19 Twitter News Feed",

abstract = "Social media platforms allow users to create and share information instantly. Due to the large amount of information on the social media platforms, some users may not be able to identify fake news. Fake news may be in a form of misinformation or disinformation and can lead to the loss of public trust on certain issues. It is crucial for social media users to detect the presence of fake news efficiently and in a timely manner. This paper aims to investigate the effectiveness of Support Vector Machine (SVM) classification approach to detect Twitter fake news. It is shown that SVM with linear kernel results in good accuracy of around 84% on independent test dataset. Furthermore, linear kernel function outperforms non-linear and polynomial kernel functions.",

author = "Wong, {W. K.} and Kong, {Jeffery T.H.} and Juwono, {Filbert H.} and Regina Reine",

note = "Publisher Copyright: {\textcopyright} The Institution of Engineering & Technology 2023.; 2023 International Conference on Green Energy, Computing and Intelligent Technology, GEn-CITy 2023 ; Conference date: 10-07-2023 Through 12-07-2023",

year = "2023",

doi = "10.1049/icp.2023.1755",

language = "English",

volume = "2023",

pages = "12--17",

journal = "IET Conference Proceedings",

issn = "2732-4494",

number = "11",

}

TY - JOUR

T1 - Language-Independent Features for Detecting Fake News

T2 - 2023 International Conference on Green Energy, Computing and Intelligent Technology, GEn-CITy 2023

AU - Wong, W. K.

AU - Kong, Jeffery T.H.

AU - Juwono, Filbert H.

AU - Reine, Regina

N1 - Publisher Copyright: © The Institution of Engineering & Technology 2023.

PY - 2023

Y1 - 2023

N2 - Social media platforms allow users to create and share information instantly. Due to the large amount of information on the social media platforms, some users may not be able to identify fake news. Fake news may be in a form of misinformation or disinformation and can lead to the loss of public trust on certain issues. It is crucial for social media users to detect the presence of fake news efficiently and in a timely manner. This paper aims to investigate the effectiveness of Support Vector Machine (SVM) classification approach to detect Twitter fake news. It is shown that SVM with linear kernel results in good accuracy of around 84% on independent test dataset. Furthermore, linear kernel function outperforms non-linear and polynomial kernel functions.

AB - Social media platforms allow users to create and share information instantly. Due to the large amount of information on the social media platforms, some users may not be able to identify fake news. Fake news may be in a form of misinformation or disinformation and can lead to the loss of public trust on certain issues. It is crucial for social media users to detect the presence of fake news efficiently and in a timely manner. This paper aims to investigate the effectiveness of Support Vector Machine (SVM) classification approach to detect Twitter fake news. It is shown that SVM with linear kernel results in good accuracy of around 84% on independent test dataset. Furthermore, linear kernel function outperforms non-linear and polynomial kernel functions.

UR - http://www.scopus.com/inward/record.url?scp=85181540735&partnerID=8YFLogxK

U2 - 10.1049/icp.2023.1755

DO - 10.1049/icp.2023.1755

M3 - Conference article

AN - SCOPUS:85181540735

SN - 2732-4494

VL - 2023

SP - 12

EP - 17

JO - IET Conference Proceedings

JF - IET Conference Proceedings

IS - 11

Y2 - 10 July 2023 through 12 July 2023

ER -

Language-Independent Features for Detecting Fake News: A Case Study of COVID-19 Twitter News Feed

Abstract

Access to Document

Other files and links

Fingerprint

Cite this