vix.ing · top · new · best · stats · spec

Words are the Window to the Soul: Language-based User Representations\n for Fake News Detection

2020/11/14 by Marco Del Tredici, Raquel Fernández, Del Tredici, Marco +1
Social Sciences · Physics and Astronomy · #Misinformation and Its Impacts #Opinion Dynamics and Social Influence #Social Media and Politics

paper · pdf · doi:10.48550/arxiv.2011.07389

Abstract

Cognitive and social traits of individuals are reflected in language use.\nMoreover, individuals who are prone to spread fake news online often share\ncommon traits. Building on these ideas, we introduce a model that creates\nrepresentations of individuals on social media based only on the language they\nproduce, and use them to detect fake news. We show that language-based user\nrepresentations are beneficial for this task. We also present an extended\nanalysis of the language of fake news spreaders, showing that its main features\nare mostly domain independent and consistent across two English datasets.\nFinally, we exploit the relation between language use and connections in the\nsocial graph to assess the presence of the Echo Chamber effect in our data.\n

Related