A Review of Deep Learning Techniques for Fake News Detection

Konferenz: ICMLCA 2021 - 2nd International Conference on Machine Learning and Computer Application
17.12.2021 - 19.12.2021 in Shenyang, China

Tagungsband: ICMLCA 2021

Seiten: 5Sprache: EnglischTyp: PDF

Persönliche VDE-Mitglieder erhalten auf diesen Artikel 10% Rabatt

Autoren:
Lin, Yufan (CAS, Boston University, Boston, MA, USA)
Shan, Zijian (School of Computer Science, China University of Geosciences, Wuhan, Hubei, China)
Zou, Siwei (School of Economics Management, Dalian University of Technology, Dalian, Liaoning, China)

Inhalt:
Fake news, as a kind of public information, releases false information to deceive people for a specific purpose. Fake news not only causes serious damage to the credibility of the public media but also damages the rights of the parties. So, it is necessary to detect fake news from both online social media and traditional media. For decades, different approaches for fake news detection have been proposed. And these methods can be categorized into manual detection and automatic detection. In this paper, we make a comprehensive review of automatic fake news detection. We first introduce the definition of fake news and fake news detection. Then, some commonly used datasets and evaluation metrics are demonstrated. Besides, we also revise some deep learning approaches for automatic fake news detection. Finally, we discuss some potential challenges and problems for the future. The survey provides a good introduction to fake news detection for both NLP researchers and social media scientists.