Context-Aware Deep Markov Random Fields for Fake News Detection

• Published in: IEEE access Vol. 9; pp. 130042 - 130054
• Main Authors: Huu Do, Tien, Berneman, Marc, Patro, Jasabanta, Bekoulis, Giannis, Deligiannis, Nikos
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial neural networks; bias detection; clickbait detection; Context; Correlation; Data mining; Deep learning; Fake news detection; Feature extraction; Fields (mathematics); Linguistics; Markov random field; News; question answering; representation learning; Representations; sentiment analysis; Social networking (online); Task analysis; Toxicity; toxicity detection; Transformers
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2021.3113877

Fake news is a serious problem, which has received considerable attention from both industry and academic communities. Over the past years, many fake news detection approaches have been introduced, and most of the existing methods rely on either news content or the social context of the news dissemination process on social media platforms. In this work, we propose a generic model that is able to take into account both the news content and the social context for the identification of fake news. Specifically, we explore different aspects of the news content by using both shallow and deep representations. The shallow representations are produced with word2vec and doc2vec models while the deep representations are generated via transformer-based models. These representations are able to jointly or separately address four individual tasks, namely bias detection, clickbait detection, sentiment analysis, and toxicity detection. In addition, we make use of graph convolutional neural networks and mean-field layers in order to exploit the underlying structural information of the news articles. That way, we are able to take into account the inherent correlation between the articles by leveraging their social context information. Experiments on widely-used benchmark datasets indicate the effectiveness of the proposed method.