A metaheuristic optimisation-based deep learning model for fake news detection in online social networks
by Chandrakant Mallick; Sarojananda Mishra; Parimal Kumar Giri; Bijay Kumar Paikaray
International Journal of Electronic Security and Digital Forensics (IJESDF), Vol. 16, No. 5, 2024

Abstract: The spread of fake news has become a societal problem. Most often, fake news spreads faster than real news and misleads society. Many works have been proposed in the literature using machine learning techniques to detect fake news, but developing a faster and more efficient model is still a challenging issue. Taking advantage of the deep neural network features of long- and short-term memory (LSTM) and metaheuristic optimisation algorithms, this paper proposes a Salp swarm algorithm-based optimised LSTM model to efficiently classify fake and real news in online social networks. To figure out the superiority of the model, it is experimentally demonstrated that the proposed model outperforms the LSTM optimised with other traditional optimisations. We tested the efficiency of the models on three datasets: the LIAR benchmark dataset, the ISOT dataset, and the news regarding the COVID-19 pandemic, and obtained accuracy of 97.89%, 86.49%, and 99.71%, respectively.

Online publication date: Mon, 02-Sep-2024

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Electronic Security and Digital Forensics (IJESDF):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com