Uncovering Coordinated Networks on Social Media: Methods and Case Studies

Abstract

Coordinated campaigns are used to influence and manipulate social media platforms and their users, a critical challenge to the free exchange of information online. Here we introduce a general, unsupervised network-based methodology to uncover groups of accounts that are likely coordinated. The proposed method constructs coordination networks based on arbitrary behavioral traces shared among accounts. We present five case studies of influence campaigns, four of which in the diverse contexts of U.S. elections, Hong Kong protests, the Syrian civil war, and cryptocurrency manipulation. In each of these cases, we detect networks of coordinated Twitter accounts by examining their identities, images, hashtag sequences, retweets, or temporal patterns. The proposed approach proves to be broadly applicable to uncover different kinds of coordination across information warfare scenarios.

VaccinEU: COVID-19 Vaccine Conversations on Twitter in French, German and Italian

“…COVID-19 vaccine uptake rates, hospitalizations, etc) in different countries. We also plan to further investigate the presence of suspicious accounts, such as bots and trolls, and provide evidence of coordinated campaigns promoting anti-vaccine messages (Pacheco et al 2021). Finally, we plan to build models to describe how online vaccine misinformation and anti-vaccine sentiment spread in different countries.…”

“…In this section we try to identify coordinated activity on the dataset by applying a coordination detection framework (Pacheco et al 2021). While coordination may occur over many different possible dimensions, here we focus our attention on coordinated sharing of URLs.…”

Super‐amplifiers! The role of Twitter extended party networks in political elections

“…In some high‐stakes events like presidential elections, politically motivated information campaigns have been carried out by coordinated networks (Pacheco et al, 2020). We also know that automated accounts (bots) can play a role in falsely amplifying political discourse in U.S. elections (Bessi & Ferrara, 2016) though others show that bots may not be effective in helping candidates gain followers (Boichak et al, 2018).…”

“…Furthermore, these reciprocal users may retweet messages posted by other users whose political convictions are similar to their own (Conover et al, 2011). Importantly, recent studies suggest that users' retweeting of the same messages may indicate coordinated behavior (Pacheco et al, 2020; Vargas et al, 2020). Based on findings from existing literature, we expect that Twitter EPNs with a high level of reciprocity are more likely to amplify political candidate's messages.…”

The Manufacture of Partisan Echo Chambers by Follow Train Abuse on Twitter

“…Features of social media like peer-to-peer communication, anonymity, high efficiency, and broad coverage greatly facilitate organization efforts (Lotan et al 2011;Starbird and Palen 2012;Tufekci and Wilson 2012). Unfortunately, the same features invite problems like inauthentic behaviors (Ferrara et al 2016;Pacheco et al 2021), echo chambers (Sasahara et al 2020), and the wide spread of toxic information (Shao et al 2018;Grinberg et al 2019;Ahmed et al 2020) that challenge the integrity of the information ecosystem. The January 6, 2021 riot at the U.S. Capitol provides clear evidence of the entanglement between online disinformation and real-world harm, 1 making it all the more crucial to study how bad actors manipulate online discourse.…”