Computer Science - Social and Information Networks
Following the 2016 US presidential election, there has been an increased
focus on politically-motivated manipulation of mass-user behavior on social
media platforms. Since a large volume of political discussion occurs on these
platforms, identifying malicious activity and coordinated campaigns is
essential to ensuring a robust democratic environment. Twitter has become a
critical communication channel for politicians and other public figures,
enabling them to maintain a direct relationship with supporters. However, the
platform has been fertile ground for large-scale malicious activity. As the
2020 U.S. presidential election approaches, we have developed tools to monitor
follower dynamics of some of the most prominent Twitter users, including U.S.
presidential candidates. We investigate numerous, strange phenomena, such as
dramatic spike and saw-tooth waveforms on follower-count charts; cohorts of
user accounts which 'circulate', i.e., re-follow high profile accounts numerous
times; and other 'resurrected' accounts, which have recently re-engaged on
Twitter after years of non-activity. So through various analyses in these
contexts, we reveal multiple, coordinated 'social' targeting campaigns aimed at
affecting the outcomes of socially critical events through the use of networks
of social automations (bots), often optimizing their social capital through
'compromised' accounts, which have--unbeknownst to the greater world--been
hijacked.
Metrics
20 Record Views
Details
Title
Investigating Coordinated 'Social' Targeting of High-Profile Twitter Accounts