Do you really follow them? Automatic detection of credulous Twitter users

TL;DR

This paper introduces a supervised classifier that accurately detects credulous Twitter users, who are more susceptible to bot influence and may unknowingly spread misinformation, achieving over 93% accuracy.

Contribution

It presents a novel method for automatically identifying credulous users on Twitter, a group previously not specifically targeted in bot detection research.

Findings

Achieved 93.27% accuracy in classifying credulous users.

High AUC-ROC of 0.93 indicates strong model performance.

Highlights the importance of detecting credulous users to combat misinformation.

Abstract

Online Social Media represent a pervasive source of information able to reach a huge audience. Sadly, recent studies show how online social bots (automated, often malicious accounts, populating social networks and mimicking genuine users) are able to amplify the dissemination of (fake) information by orders of magnitude. Using Twitter as a benchmark, in this work we focus on what we define credulous users, i.e., human-operated accounts with a high percentage of bots among their followings. Being more exposed to the harmful activities of social bots, credulous users may run the risk of being more influenced than other users; even worse, although unknowingly, they could become spreaders of misleading information (e.g., by retweeting bots). We design and develop a supervised classifier to automatically recognize credulous users. The best tested configuration achieves an accuracy of 93.27% and AUC-ROC of 0.93, thus leading to positive and encouraging results.