Multiple features based approach for automatic fake news detection on social networks using deep learning

In recent years, the rise of Online Social Networks has led to proliferation of social news such as product advertisement, political news, celebrity's information, etc. Some of the social networks such as Facebook, Instagram and Twitter affected by their user through fake news. Unfortunately, some users use unethical means to grow their links and reputation by spreading fake news in the form of texts, images, and videos. However, the recent information appearing on an online social network is doubtful, and in many cases, it misleads other users in the network. Fake news is spread intentionally to mislead readers to believe false news, which makes it difficult for detection mechanism to detect fake news on the basis of shared content. Therefore, we need to add some new information related to user's profile, such as user's involvement with others for finding a particular decision. The disseminated information and their diffusion process create a big problem for detecting these contents promptly and thus highlighting the need for automatic fake news detection. In this paper, we are going to introduce automatic fake news detection approach in chrome environment on which it can detect fake news on Facebook. Specifically, we use multiple features associated with Facebook account with some news content features to analyze the behavior of the account through deep learning. The experimental analysis of real-world information demonstrates that our intended fake news detection approach has achieved higher accuracy than the existing state of art techniques. (c) 2020 Elsevier B.V. All rights reserved.

Automated summary

In recent years, the proliferation of fake news on online social networks has become a serious issue, prompting the need for improved detection and prevention methods. This paper introduces an automatic fake news detection approach based on user profile information and deep learning, which has shown to increase detection accuracy.