Fighting the Fake: A Forensic Linguistic Analysis to Fake News Detection

Fake news has been the focus of debate, especially since the election of Donald Trump (2016), and remains a topic of concern in democratic countries worldwide, given (a) their threat to democratic systems and (b) the difficulty in detecting them. Despite the deployment of sophisticated computational systems to identify fake news, as well as the streamlining of fact-checking methods, appropriate fake news detection mechanisms have not yet been found. In fact, technological approaches are likely to be inefficient, given that fake news are based mostly on partisanship and identity politics, and not necessarily on outright deception. However, as disinformation is inherently expressed linguistically, this is a privileged room for forensic linguistic analysis. This article builds upon a forensic linguistic analysis of fake news pieces published in English and in Portuguese, which were collected since 2019 from acknowledged fake news outlets. The preliminary empirical analysis reveals that fake news pieces employ particular linguistic features, e.g. at the levels of typography, orthography and spelling, and morphosyntax. The systematic identification of these features, which will allow mapping linguistic resources and patterns used in those contexts, contributes to scholarship, not only by enabling a streamlined development of computational detection systems, but more importantly by permitting the forensic linguistics expert to assist criminal investigations and give evidence in court.