Characterizing Retweet Bots: The Case of Black Market Accounts

TL;DR

This paper investigates retweet bots acquired from the black market, analyzing their behaviors, differences from human accounts, and challenging existing detection assumptions to better understand their role in social media manipulation.

Contribution

It provides a detailed characterization of retweet bots from the black market, revealing their behaviors, lifecycle, and differences from human accounts, and questions prior detection methods.

Findings

Retweet bots exhibit unique behaviors and lifecycle patterns.

There are significant differences between black market retweet bots and previously studied bots.

Current detection assumptions may be ineffective against these retweet bots.

Abstract

Malicious Twitter bots are detrimental to public discourse on social media. Past studies have looked at spammers, fake followers, and astroturfing bots, but retweet bots, which artificially inflate content, are not well understood. In this study, we characterize retweet bots that have been uncovered by purchasing retweets from the black market. We detect whether they are fake or genuine accounts involved in inauthentic activities and what they do in order to appear legitimate. We also analyze their differences from human-controlled accounts. From our findings on the nature and life-cycle of retweet bots, we also point out several inconsistencies between the retweet bots used in this work and bots studied in prior works. Our findings challenge some of the fundamental assumptions related to bots and in particular how to detect them.