The Anatomy of Conspirators: Unveiling Traits using a Comprehensive Twitter Dataset

TL;DR

This study constructs a comprehensive Twitter dataset of 15,000 accounts involved in conspiracy activities and analyzes their traits, behaviors, and topics, revealing significant behavioral differences from control users and enabling high-accuracy classification.

Contribution

The paper introduces a novel, large-scale dataset of conspiracy-related Twitter accounts and develops a highly accurate classifier to identify such users based on behavioral and linguistic features.

Findings

Conspiracy and control users have similar profile metadata.

Behavioral and topical differences are significant between groups.

The classifier achieves an F1 score of 0.94 in identifying conspiracy users.

Abstract

The discourse around conspiracy theories is currently thriving amidst the rampant misinformation in online environments. Research in this field has been focused on detecting conspiracy theories on social media, often relying on limited datasets. In this study, we present a novel methodology for constructing a Twitter dataset that encompasses accounts engaged in conspiracy-related activities throughout the year 2022. Our approach centers on data collection that is independent of specific conspiracy theories and information operations. Additionally, our dataset includes a control group comprising randomly selected users who can be fairly compared to the individuals involved in conspiracy activities. This comprehensive collection effort yielded a total of 15K accounts and 37M tweets extracted from their timelines. We conduct a comparative analysis of the two groups across three dimensions: topics, profiles, and behavioral characteristics. The results indicate that conspiracy and control users exhibit similarity in terms of their profile metadata characteristics. However, they diverge significantly in terms of behavior and activity, particularly regarding the discussed topics, the terminology used, and their stance on trending subjects. In addition, we find no significant disparity in the presence of bot users between the two groups. Finally, we develop a classifier to identify conspiracy users using features borrowed from bot, troll and linguistic literature. The results demonstrate a high accuracy level (with an F1 score of 0.94), enabling us to uncover the most discriminating features associated with conspiracy-related accounts.