Misleading Repurposing on Twitter

Abstract

We present the first in-depth and large-scale study of misleading repurposing, in which a malicious user changes the identity of their social media account via, among other things, changes to the profile attributes in order to use the account for a new purpose while retaining their followers. We propose a definition for the behavior and a methodology that uses supervised learning on data mined from the Internet Archive's Twitter Stream Grab to flag repurposed accounts. We found over 100,000 accounts that may have been repurposed. Of those, 28% were removed from the platform after 2 years, thereby confirming their inauthenticity. We also characterize repurposed accounts and found that they are more likely to be repurposed after a period of inactivity and deleting old tweets. We also provide evidence that adversaries target accounts with high follower counts to repurpose, and some make them have high follower counts by participating in follow-back schemes. The results we present have implications for the security and integrity of social media platforms, for data science studies in how historical data is considered, and for society at large in how users can be deceived about the popularity of an opinion. The data and the code is available at https://github.com/tugrulz/MisleadingRepurposing.

Shorts vs. Regular Videos on YouTube: A Comparative Analysis of User Engagement and Content Creation Trends

“…For instance, users tend to use more abbreviations and contracted forms when they are constrained by the length of their content, but they also tend to create content with better quality [12]. They may also game platforms' policies to manipulate social media, such as purchasing popular accounts instead of growing new accounts [11] or maintaining backup accounts to recover from platform suspensions [24]. Other actors such as researchers may also be affected by platforms' data collection policies such as denying access to removed content [9] or limiting access to the API [5].…”

#TeamFollowBack: Detection & Analysis of Follow Back Accounts on Social Media

“…Illicitly growing social media accounts is also a manipulation strategy. Adversaries may grow their accounts by buying fake followers (Cresci et al 2015), buying and repurposing entire accounts (Elmas, Overdorf, and Aberer 2023), riding "follow trains" (i.e., being recommended by other accounts explicitly) (Torres-Lugo, Yang, and Menczer 2020), maintaining backup accounts (Merhi, Rajtmajer, and Lee 2023), or authoring viral tweets (Elmas, Stephane, and Houssiaux 2023). Some social media accounts abuse reciprocity to illicitly grow their accounts.…”

“…Additionally, follow back accounts may sometimes follow spam or fake profiles which may inadvertently amplify such harmful profiles. Even though such accounts have initially benign goals despite their misleading follower counts, they may be later sold to adversaries who exploit their large audience to spread misleading content (Elmas, Overdorf, and Aberer 2023).…”