QANON ON TWITTER: A DATA-DRIVEN APPROACH TO TACKLING THE SPREAD OF A RELENTLESS CONSPIRACY

Abstract

QAnon is a highly addictive conspiracy theory that plagues social media, destabilizes democracy and incites violence. Using a data set of nearly 1 million tweets related to QAnon this study applies network analysis, topic modeling and classification techniques to better understand the essence of QAnon on Twitter. We find that the vast majority of users engrossed by QAnon are highly polarized and isolated from other users and furthermore that only a few sources of authority connect an otherwise modular network. This paper also finds training Logistic Regression, Naïve Bayes and Support Vector Machine classifiers on a user’s historical tweets leads to accurate classification of accounts most at risk of fixation with the conspiracy.