The Use of Syntactic Information in Fake News Detection: A Systematic Review

Abstract

Fake news has been a critical problem for society, to the extent that its damaging effects can already be seen in several areas, such as democracy and health. However, as fake news grow in number, manual fact-checking becomes impractical for identifying them, which makes automatic detection a compelling alternative. In this sense, this study gathers multiple solutions for the problem of automatically detecting fake news, through the usage of both lexical and syntactic information. This study consists of a systematic review on fake news detection through linguistic patterns, focusing on the use of syntax to aid in the task. Solving complex problems by capturing linguistic patterns is mostly explored in the Natural Language Processing (NLP) area. In general, the use of shallow syntax representations, such as Parts of speech, only marginally increases the performance of classifiers in this task. However, relying on deeper syntactic representations, such as context-free grammars or syntactic dependency trees, present more promising results.