Identification of Fake News Using Deep Neural Network-Based Hybrid Model

• Published in: SN computer science 2023-09, Vol.4 (5), p.679, Article 679
• Main Authors: Gupta, Sonam, Verma, Bhanu, Gupta, Pradeep, Goel, Lipika, Yadav, Arun Kumar, Yadav, Divakar
• Format: Article
• Language: English
• Subjects: Algorithms; Artificial neural networks; Computer Imaging; Computer Science; Computer Systems Organization and Communication Networks; Coronaviruses; Data Structures and Information Theory; Datasets; Deep learning; Digital media; False information; Information Systems and Communication Service; Internet; Machine learning; Neural networks; News; Original Research; Pandemics; Pattern Recognition and Graphics; Political parties; Research Trends in Communication and Network Technologies; Social networks; Society; Software Engineering/Programming and Operating Systems; Support vector machines; User behavior; Vision
• ISSN: 2661-8907; 2662-995X; 2661-8907
• DOI: 10.1007/s42979-023-02117-0

The current era of social digitization and exponential growth of social media decreases the distance between people to connect with each other. Due to increasing the massive information on social media networks such as Facebook, Twitter and Instagram etc., it also increases the fake/incorrect information among users. This fake/incorrect information may cause severe effects on various levels of society, i.e., individuals (depression, increased death rate etc.), political (influenced by some political party for harm/benefit), religion and society etc. In this paper, we initially proposed machine learning models as a baseline and, later, a hybrid deep learning model (CNN + LSTM) for detecting fake/real news on text and image datasets. Finally, a comparative analysis is conducted with state-of-the-art to validate the proposed model. The experimental evaluation reveals that the proposed model achieved 96.1% accuracy on text news and 91.36% on image news data.