exBAKE: Automatic fake news detection model based on Bidirectional Encoder Representations from Transformers (BERT)

Heejung Jwa, Dongsuk Oh, Kinam Park, Jang Mook Kang, Heuiseok Lim

Research output: Contribution to journalArticle

Abstract

News currently spreads rapidly through the internet. Because fake news stories are designed to attract readers, they tend to spread faster. For most readers, detecting fake news can be challenging and such readers usually end up believing that the fake news story is fact. Because fake news can be socially problematic, a model that automatically detects such fake news is required. In this paper, we focus on data-driven automatic fake news detection methods. We first apply the Bidirectional Encoder Representations from Transformers model (BERT) model to detect fake news by analyzing the relationship between the headline and the body text of news. To further improve performance, additional news data are gathered and used to pre-train this model. We determine that the deep-contextualizing nature of BERT is best suited for this task and improves the 0.14 F-score over older state-of-the-art models.

Original languageEnglish
Article number4062
JournalApplied Sciences (Switzerland)
Volume9
Issue number19
DOIs
Publication statusPublished - 2019 Oct 1

Fingerprint

news
coders
transformers
readers
Internet

Keywords

  • Deep learning
  • Fake information
  • Fake news
  • Fake news challenge
  • Fake news classification
  • Fake news detect

ASJC Scopus subject areas

  • Materials Science(all)
  • Instrumentation
  • Engineering(all)
  • Process Chemistry and Technology
  • Computer Science Applications
  • Fluid Flow and Transfer Processes

Cite this

exBAKE : Automatic fake news detection model based on Bidirectional Encoder Representations from Transformers (BERT). / Jwa, Heejung; Oh, Dongsuk; Park, Kinam; Kang, Jang Mook; Lim, Heuiseok.

In: Applied Sciences (Switzerland), Vol. 9, No. 19, 4062, 01.10.2019.

Research output: Contribution to journalArticle

@article{744bb09e894344d38107ea74d1439984,
title = "exBAKE: Automatic fake news detection model based on Bidirectional Encoder Representations from Transformers (BERT)",
abstract = "News currently spreads rapidly through the internet. Because fake news stories are designed to attract readers, they tend to spread faster. For most readers, detecting fake news can be challenging and such readers usually end up believing that the fake news story is fact. Because fake news can be socially problematic, a model that automatically detects such fake news is required. In this paper, we focus on data-driven automatic fake news detection methods. We first apply the Bidirectional Encoder Representations from Transformers model (BERT) model to detect fake news by analyzing the relationship between the headline and the body text of news. To further improve performance, additional news data are gathered and used to pre-train this model. We determine that the deep-contextualizing nature of BERT is best suited for this task and improves the 0.14 F-score over older state-of-the-art models.",
keywords = "Deep learning, Fake information, Fake news, Fake news challenge, Fake news classification, Fake news detect",
author = "Heejung Jwa and Dongsuk Oh and Kinam Park and Kang, {Jang Mook} and Heuiseok Lim",
year = "2019",
month = "10",
day = "1",
doi = "10.3390/app9194062",
language = "English",
volume = "9",
journal = "Applied Sciences (Switzerland)",
issn = "2076-3417",
publisher = "Multidisciplinary Digital Publishing Institute",
number = "19",

}

TY - JOUR

T1 - exBAKE

T2 - Automatic fake news detection model based on Bidirectional Encoder Representations from Transformers (BERT)

AU - Jwa, Heejung

AU - Oh, Dongsuk

AU - Park, Kinam

AU - Kang, Jang Mook

AU - Lim, Heuiseok

PY - 2019/10/1

Y1 - 2019/10/1

N2 - News currently spreads rapidly through the internet. Because fake news stories are designed to attract readers, they tend to spread faster. For most readers, detecting fake news can be challenging and such readers usually end up believing that the fake news story is fact. Because fake news can be socially problematic, a model that automatically detects such fake news is required. In this paper, we focus on data-driven automatic fake news detection methods. We first apply the Bidirectional Encoder Representations from Transformers model (BERT) model to detect fake news by analyzing the relationship between the headline and the body text of news. To further improve performance, additional news data are gathered and used to pre-train this model. We determine that the deep-contextualizing nature of BERT is best suited for this task and improves the 0.14 F-score over older state-of-the-art models.

AB - News currently spreads rapidly through the internet. Because fake news stories are designed to attract readers, they tend to spread faster. For most readers, detecting fake news can be challenging and such readers usually end up believing that the fake news story is fact. Because fake news can be socially problematic, a model that automatically detects such fake news is required. In this paper, we focus on data-driven automatic fake news detection methods. We first apply the Bidirectional Encoder Representations from Transformers model (BERT) model to detect fake news by analyzing the relationship between the headline and the body text of news. To further improve performance, additional news data are gathered and used to pre-train this model. We determine that the deep-contextualizing nature of BERT is best suited for this task and improves the 0.14 F-score over older state-of-the-art models.

KW - Deep learning

KW - Fake information

KW - Fake news

KW - Fake news challenge

KW - Fake news classification

KW - Fake news detect

UR - http://www.scopus.com/inward/record.url?scp=85073295962&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85073295962&partnerID=8YFLogxK

U2 - 10.3390/app9194062

DO - 10.3390/app9194062

M3 - Article

AN - SCOPUS:85073295962

VL - 9

JO - Applied Sciences (Switzerland)

JF - Applied Sciences (Switzerland)

SN - 2076-3417

IS - 19

M1 - 4062

ER -