Fraudulent News Headline Detection with Attention Mechanism

Hankun Liu; Daojing He; Sammy Chan

doi:10.1155/2021/6679661

Fraudulent News Headline Detection with Attention Mechanism

Hankun Liu
, Daojing He^*
, Sammy Chan

^*Corresponding author for this work

East China Normal University
City University of Hong Kong

Research output: Contribution to journal › Article › peer-review

6 Scopus citations

Abstract

E-mail systems and online social media platforms are ideal places for news dissemination, but a serious problem is the spread of fraudulent news headlines. The previous method of detecting fraudulent news headlines was mainly laborious manual review. While the total number of news headlines goes as high as 1.48 million, manual review becomes practically infeasible. For news headline text data, attention mechanism has powerful processing capability. In this paper, we propose the models based on LSTM and attention layer, which fit the context of news headlines efficiently and can detect fraudulent news headlines quickly and accurately. Based on multi-head attention mechanism eschewing recurrent unit and reducing sequential computation, we build Mini-Transformer Deep Learning model to further improve the classification performance.

Original language	English
Article number	6679661
Journal	Computational Intelligence and Neuroscience
Volume	2021
DOIs	https://doi.org/10.1155/2021/6679661
State	Published - 2021
Externally published	Yes

Access to Document

10.1155/2021/6679661

Cite this

@article{fc884013841e44e8a3343fd9dac34a57,

title = "Fraudulent News Headline Detection with Attention Mechanism",

abstract = "E-mail systems and online social media platforms are ideal places for news dissemination, but a serious problem is the spread of fraudulent news headlines. The previous method of detecting fraudulent news headlines was mainly laborious manual review. While the total number of news headlines goes as high as 1.48 million, manual review becomes practically infeasible. For news headline text data, attention mechanism has powerful processing capability. In this paper, we propose the models based on LSTM and attention layer, which fit the context of news headlines efficiently and can detect fraudulent news headlines quickly and accurately. Based on multi-head attention mechanism eschewing recurrent unit and reducing sequential computation, we build Mini-Transformer Deep Learning model to further improve the classification performance.",

author = "Hankun Liu and Daojing He and Sammy Chan",

note = "Publisher Copyright: {\textcopyright} 2021 Hankun Liu et al.",

year = "2021",

doi = "10.1155/2021/6679661",

language = "英语",

volume = "2021",

journal = "Computational Intelligence and Neuroscience",

issn = "1687-5265",

publisher = "Hindawi Publishing Corporation",

}

TY - JOUR

T1 - Fraudulent News Headline Detection with Attention Mechanism

AU - Liu, Hankun

AU - He, Daojing

AU - Chan, Sammy

PY - 2021

Y1 - 2021

N2 - E-mail systems and online social media platforms are ideal places for news dissemination, but a serious problem is the spread of fraudulent news headlines. The previous method of detecting fraudulent news headlines was mainly laborious manual review. While the total number of news headlines goes as high as 1.48 million, manual review becomes practically infeasible. For news headline text data, attention mechanism has powerful processing capability. In this paper, we propose the models based on LSTM and attention layer, which fit the context of news headlines efficiently and can detect fraudulent news headlines quickly and accurately. Based on multi-head attention mechanism eschewing recurrent unit and reducing sequential computation, we build Mini-Transformer Deep Learning model to further improve the classification performance.

AB - E-mail systems and online social media platforms are ideal places for news dissemination, but a serious problem is the spread of fraudulent news headlines. The previous method of detecting fraudulent news headlines was mainly laborious manual review. While the total number of news headlines goes as high as 1.48 million, manual review becomes practically infeasible. For news headline text data, attention mechanism has powerful processing capability. In this paper, we propose the models based on LSTM and attention layer, which fit the context of news headlines efficiently and can detect fraudulent news headlines quickly and accurately. Based on multi-head attention mechanism eschewing recurrent unit and reducing sequential computation, we build Mini-Transformer Deep Learning model to further improve the classification performance.

UR - https://www.scopus.com/pages/publications/85105325542

U2 - 10.1155/2021/6679661

DO - 10.1155/2021/6679661

M3 - 文章

C2 - 33959157

AN - SCOPUS:85105325542

SN - 1687-5265

VL - 2021

JO - Computational Intelligence and Neuroscience

JF - Computational Intelligence and Neuroscience

M1 - 6679661

ER -

Fraudulent News Headline Detection with Attention Mechanism

Abstract

Access to Document

Other files and links

Fingerprint

Cite this