00 Acta Scientific | International Open Library | Open Access Journals Publishing Group

Acta Scientific Computer Sciences

Review Article Volume 2 Issue 11

Fake News Identification Using Recurrent Neural Network Augmented with Cellular Automata

Pokkuluri Kiran Sree1* and SSSN Usha Devi N2

1Professor, Department of CSE, Shri Vishnu Engineering College for Women, Bhimavaram, AP, India
2Assistant Professor, Department of CSE, University College of Engineering-Kakinada, JNTU-K, AP, India

*Corresponding Author:Pokkuluri Kiran Sree, Professor, Department of CSE, Shri Vishnu Engineering College for Women, Bhimavaram, AP, India.

Received: October 14, 2020; Published: October 28, 2020

×

Abstract

  Fake news propagation is identified as the most alarming problem in India. The use of social media has an immense effect on the business, culture and society; it is one of the sources/spread of fake news. We propose a novel, robust framework with Recurrent Neural Network Augmented with Cellular Automata (RNN-CA), which was trained and tested with standard datasets taken from Kaggle and other prominent news websites to identify the fake messages. The proposed approach meticulously identifies the set of features needed to predict the fake news and messages with an average accuracy of 89.76%. We have used various parameters like specificity, sensitivity and average accuracy for validating our classifier. RNN-CA performance is compared with the existing literature and it was found promising.

Keywords: Fake News; Recurrent Neural Network (RNN); Cellular Automata (CA)

×

Citation

Citation: Pokkuluri Kiran Sree and SSSN Usha Devi N. "Fake News Identification Using Recurrent Neural Network Augmented with Cellular Automata". Acta Scientific Computer Sciences 2.11 (2020): 39-41.




Metrics

Acceptance rate35%
Acceptance to publication20-30 days

Indexed In




News and Events


  • Certification for Review
    Acta Scientific certifies the Editors/reviewers for their review done towards the assigned articles of the respective journals.
  • Submission Timeline for Upcoming Issue
    The last date for submission of articles for regular Issues is December 25, 2024.
  • Publication Certificate
    Authors will be issued a "Publication Certificate" as a mark of appreciation for publishing their work.
  • Best Article of the Issue
    The Editors will elect one Best Article after each issue release. The authors of this article will be provided with a certificate of "Best Article of the Issue"

Contact US