Fraudulent News Headline Detection with Attention Mechanism.
Journal
Computational intelligence and neuroscience
ISSN: 1687-5273
Titre abrégé: Comput Intell Neurosci
Pays: United States
ID NLM: 101279357
Informations de publication
Date de publication:
2021
2021
Historique:
received:
28
11
2020
revised:
03
02
2021
accepted:
27
02
2021
entrez:
7
5
2021
pubmed:
8
5
2021
medline:
29
7
2021
Statut:
epublish
Résumé
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.
Identifiants
pubmed: 33959157
doi: 10.1155/2021/6679661
pmc: PMC8075658
doi:
Types de publication
News
Langues
eng
Sous-ensembles de citation
IM
Pagination
6679661Informations de copyright
Copyright © 2021 Hankun Liu et al.
Déclaration de conflit d'intérêts
The authors declare that there are no conflicts of interest regarding the publication of this paper.
Références
Neural Comput. 1997 Nov 15;9(8):1735-80
pubmed: 9377276