Research Area:  Machine Learning

Abstract:

Fake news, particularly with the speed and reach of unverified/false information dissemination, is a troubling trend with potential political and societal consequences, as evidenced in the 2016 United States presidential election, the ongoing COVID-19 pandemic, and the ongoing protests. To mitigate such threats, a broad range of approaches have been designed to detect and mitigate online fake news. In this paper, we systematically review existing fake news mitigation and detection approaches, and identify a number of challenges and potential research opportunities (e.g., the importance of a data sharing platform that can also be used to facilitate machine or deep learning). We hope that the findings reported in this paper will motivate further research in this area.

Keywords:  

Author(s) Name:  Saqib Hakak, Wazir Zada Khan, Sweta Bhattacharya, G.Thippa Reddy, Kim-Kwang Raymond Choo

Publisher name:  Springer

DOI:  https://doi.org/10.1007/978-3-030-66046-8_28

Volume Information:  pages 345-353

Paper Link:   https://link.springer.com/chapter/10.1007/978-3-030-66046-8_28