Which machine learning paradigm for fake news detection?

Abstract

Fake news detection/classification is gradually becoming of paramount importance to out society in order to avoid the so-called reality vertigo, and protect in particular the less educated persons. Various machine learning techniques have been proposed to address this issue. This article presents a comprehensive performance evaluation of eight machine learning algorithms for fake news detection/classification. CCS CONCEPTS • General and reference → Evaluation; • Human-centered computing → Collaborative and social computing design and evaluation methods; Social network analysis.