Multi-Label Fake News Detection using Multi-layered Supervised Learning

Rapid spreading of misinformation is a growing worldwide concern as it has the capacity to greatly influence individual reputation and societal behavior. The consequences of unchecked spreading of misinformation can not only vary from political to financial but also effect global opinion for a long time. Thus, detecting fake news is important but challenging as the ability to accurately categorize certain information as true or fake is limited even in human. Moreover, fake news are a blend of correct news and false information making accurate classification even more confusing. In this paper, we propose a novel method of multilevel multiclass fake news detection based on relabeling of the dataset and learning iteratively. The proposed method outperforms the benchmark and our experiments indicate that profile of the source of information contributes the most in fake news detection.