Mc-DNN: Fake News Detection Using Multi-Channel Deep Neural Networks

Mc-DNN: Fake News Detection Using Multi-Channel Deep Neural Networks

Jitendra Vikram Tembhurne, Md. Moin Almin, Tausif Diwan
Copyright: © 2022 |Pages: 20
DOI: 10.4018/IJSWIS.295553
Article PDF Download
Open access articles are freely available for download

Abstract

With the advancement of technology, social media has become a major source of digital news due to its global exposure. This has led to an increase in spreading fake news and misinformation online. Humans cannot differentiate fake news from real news because they can be easily influenced. A lot of research work has been conducted for detecting fake news using Artificial Intelligence and Machine Learning. A large number of deep learning models and their architectural variants have been investigated and many websites are utilizing these models directly or indirectly to detect fake news. However, state-of-the-arts demonstrate the limited accuracy in distinguishing fake news from the original news. We propose a multi-channel deep learning model namely Mc-DNN, leveraging and processing the news headlines and news articles along different channels for differentiating fake or real news. We achieve the highest accuracy of 99.23% on ISOT Fake News Dataset and 94.68% on Fake News Data for Mc-DNN. Thus, we highly recommend the use of Mc-DNN for fake news detection.
Article Preview
Top

Introduction

As of 2019, 86.6% of the world population in the developed world has an access to the internet (Statista, 2019) and a person spends an average time of 2:22 (hh:mm) daily on various social media accounts (Review42, 2016). Due to the ease of internet access, it’s natural for people to search and follow news from various social media platforms instead of traditional news media such as newspapers and televisions. The main reasons behind this spike in online news reading are the ease of availability of timely news, nice presentation, better recommendations, and less expensive related to the traditional means. Moreover, social media allows its users to share, comment, and discuss the news with an individual, followers, groups, or in public domain. For example, around 62% news from social media read by the adults of U.S. in 2016, a considerable enhancement from 49% as compared to 2012 (Gottfried & Shearer, 2016). Nevertheless, social media news are outperforming the news appearing on the television (BBC News, 2020). However, like the two sides of a coin, there is a major flaw in the availability and authenticity of news posted on social media. The quality of the news articles posted on these online portals is relatively lower than those published by reputed news agencies and their online prints. Moreover, the credibility of the news is little bit uncertain that might produce the possibilities of spreading fake news in the community.

Fake news is the spread of disinformation through news channels, print media or online platforms i.e. social media, mostly fake news are deliberated to misguide the people in large. Due to the digital platforms, we witness the rapid increase in fake news. The dissemination of fake news is often targeted to damage the image of a person, group, or community. Furthermore, these news are nicely fabricated to catch the headlines by reaching more people. Moreover, advertising agencies earns revenue from such fake news posted as a headlines and clickbait stories in online (Wikipedia: Fake News, 2020). Nearly, half of the readers report that they see fake news stories on their social media at least once a day. Our automated model shall help individuals, industries and firms to detect and identify the authenticity of the news. There is a huge impact on the shares of the companies on the basis of these fraudulent news. As we incorporate both news headlines and news articles to detect the authenticity, higher confidence is provided to its stakeholders in terms of fake news detection accuracy.

In Figure 1 (a), we can see the perceived frequency of online news websites reporting fake news stories in the U.S. (March 2018). In U.S., fake news was reported by the news websites is about 52%, fake news was occasionally reported by the news website is about 34%, and only 9% confirmed that no fake news being reported online (Statista, 2020). A Survey conducted by the American Trends Panel in March-April 2014, shows that Facebook was the highest communicator of fake news (Pew Research Center, 2015). The result of the survey is shown in Figure 1 (b). Overall, the spread of disinformation could incite political violence, sabotage elections, and unsettle diplomatic relations leading to the deterioration of conflicts. As people are more inclined to believe what they see and read, fake news is an especially dangerous tool to spread of unverified information - an issue made worse by how quickly and easily social media platforms can be used to facilitate this spread (BIC, 2020).

Figure 1a.

Fake news reported by news website in U.S. (March 2018)

IJSWIS.295553.f01a
Figure 1b.

% of people received news about politics and government from different sources.

IJSWIS.295553.f01b

Complete Article List

Search this Journal:
Reset
Volume 20: 1 Issue (2024)
Volume 19: 1 Issue (2023)
Volume 18: 4 Issues (2022): 2 Released, 2 Forthcoming
Volume 17: 4 Issues (2021)
Volume 16: 4 Issues (2020)
Volume 15: 4 Issues (2019)
Volume 14: 4 Issues (2018)
Volume 13: 4 Issues (2017)
Volume 12: 4 Issues (2016)
Volume 11: 4 Issues (2015)
Volume 10: 4 Issues (2014)
Volume 9: 4 Issues (2013)
Volume 8: 4 Issues (2012)
Volume 7: 4 Issues (2011)
Volume 6: 4 Issues (2010)
Volume 5: 4 Issues (2009)
Volume 4: 4 Issues (2008)
Volume 3: 4 Issues (2007)
Volume 2: 4 Issues (2006)
Volume 1: 4 Issues (2005)
View Complete Journal Contents Listing