Fagon: Fake news detection model using grammatical transformation on deep neural network

Youngkyung Seo, Seong Soo Han, You Boo Jeon, Chang Sung Jeong

Research output: Contribution to journalArticle

Abstract

As technology advances, the amount of fake news is increasing more and more by various reasons such as political issues and advertisement exaggeration. However, there have been very few research works on fake news detection, especially which uses grammatical transformation on deep neural network. In this paper, we shall present a new Fake News Detection Model, called FAGON(Fake news detection model using Grammatical transformation On deep Neural network) which determines efficiently if the proposition is true or not for the given article by learning grammatical transformation on neural network. Especially, our model focuses the Korean language. It consists of two modules: sentence generator and classification. The former generates multiple sentences which have the same meaning as the proposition, but with different grammar by training the grammatical transformation. The latter classifies the proposition as true or false by training with vectors generated from each sentence of the article and the multiple sentences obtained from the former model respectively. We shall show that our model is designed to detect fake news effectively by exploiting various grammatical transformation and proper classification structure.

Original languageEnglish
Pages (from-to)4958-4970
Number of pages13
JournalKSII Transactions on Internet and Information Systems
Volume13
Issue number10
DOIs
Publication statusPublished - 2019 Oct 30

Fingerprint

Deep neural networks
Neural networks

Keywords

  • Deep neural network
  • Fake news detection
  • Grammatical transformation

ASJC Scopus subject areas

  • Information Systems
  • Computer Networks and Communications

Cite this

Fagon : Fake news detection model using grammatical transformation on deep neural network. / Seo, Youngkyung; Han, Seong Soo; Jeon, You Boo; Jeong, Chang Sung.

In: KSII Transactions on Internet and Information Systems, Vol. 13, No. 10, 30.10.2019, p. 4958-4970.

Research output: Contribution to journalArticle

@article{62c43a32b3ab4fff9a07983a772b37c2,
title = "Fagon: Fake news detection model using grammatical transformation on deep neural network",
abstract = "As technology advances, the amount of fake news is increasing more and more by various reasons such as political issues and advertisement exaggeration. However, there have been very few research works on fake news detection, especially which uses grammatical transformation on deep neural network. In this paper, we shall present a new Fake News Detection Model, called FAGON(Fake news detection model using Grammatical transformation On deep Neural network) which determines efficiently if the proposition is true or not for the given article by learning grammatical transformation on neural network. Especially, our model focuses the Korean language. It consists of two modules: sentence generator and classification. The former generates multiple sentences which have the same meaning as the proposition, but with different grammar by training the grammatical transformation. The latter classifies the proposition as true or false by training with vectors generated from each sentence of the article and the multiple sentences obtained from the former model respectively. We shall show that our model is designed to detect fake news effectively by exploiting various grammatical transformation and proper classification structure.",
keywords = "Deep neural network, Fake news detection, Grammatical transformation",
author = "Youngkyung Seo and Han, {Seong Soo} and Jeon, {You Boo} and Jeong, {Chang Sung}",
year = "2019",
month = "10",
day = "30",
doi = "10.3837/tiis.2019.10.008",
language = "English",
volume = "13",
pages = "4958--4970",
journal = "KSII Transactions on Internet and Information Systems",
issn = "1976-7277",
publisher = "Korea Society of Internet Information",
number = "10",

}

TY - JOUR

T1 - Fagon

T2 - Fake news detection model using grammatical transformation on deep neural network

AU - Seo, Youngkyung

AU - Han, Seong Soo

AU - Jeon, You Boo

AU - Jeong, Chang Sung

PY - 2019/10/30

Y1 - 2019/10/30

N2 - As technology advances, the amount of fake news is increasing more and more by various reasons such as political issues and advertisement exaggeration. However, there have been very few research works on fake news detection, especially which uses grammatical transformation on deep neural network. In this paper, we shall present a new Fake News Detection Model, called FAGON(Fake news detection model using Grammatical transformation On deep Neural network) which determines efficiently if the proposition is true or not for the given article by learning grammatical transformation on neural network. Especially, our model focuses the Korean language. It consists of two modules: sentence generator and classification. The former generates multiple sentences which have the same meaning as the proposition, but with different grammar by training the grammatical transformation. The latter classifies the proposition as true or false by training with vectors generated from each sentence of the article and the multiple sentences obtained from the former model respectively. We shall show that our model is designed to detect fake news effectively by exploiting various grammatical transformation and proper classification structure.

AB - As technology advances, the amount of fake news is increasing more and more by various reasons such as political issues and advertisement exaggeration. However, there have been very few research works on fake news detection, especially which uses grammatical transformation on deep neural network. In this paper, we shall present a new Fake News Detection Model, called FAGON(Fake news detection model using Grammatical transformation On deep Neural network) which determines efficiently if the proposition is true or not for the given article by learning grammatical transformation on neural network. Especially, our model focuses the Korean language. It consists of two modules: sentence generator and classification. The former generates multiple sentences which have the same meaning as the proposition, but with different grammar by training the grammatical transformation. The latter classifies the proposition as true or false by training with vectors generated from each sentence of the article and the multiple sentences obtained from the former model respectively. We shall show that our model is designed to detect fake news effectively by exploiting various grammatical transformation and proper classification structure.

KW - Deep neural network

KW - Fake news detection

KW - Grammatical transformation

UR - http://www.scopus.com/inward/record.url?scp=85076016496&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85076016496&partnerID=8YFLogxK

U2 - 10.3837/tiis.2019.10.008

DO - 10.3837/tiis.2019.10.008

M3 - Article

AN - SCOPUS:85076016496

VL - 13

SP - 4958

EP - 4970

JO - KSII Transactions on Internet and Information Systems

JF - KSII Transactions on Internet and Information Systems

SN - 1976-7277

IS - 10

ER -