Characterizing the Internet Research Agency’s Social Media Operations During the 2016 U.S. Presidential Election using Linguistic Analyses

Abstract

Converging investigations on the part of multiple agencies/agents have provided overwhelming evidence for Russian interference in the 2016 U.S. presidential election. As a part (and consequence) of recent reports, multiple datasets that capture actions taken by actors of the Internet Research Agency (IRA), have been released to the public. In the cur-rent paper, we present and abridged report of several preliminary forensic analyses of Facebook ad data and Twitter troll accounts that were run by the IRA during the election cycle. Through the use of language analysis, we characterize the evolution of IRA content over the course of the election cycle, providing a basis for understanding how left- and right-leaning ideologies were differentially targeted to spread enmity among the American electorate. Additionally, through an analysis of syntactic constructions, we find that the content produced by the IRA on Twitter was linguistically unique from a control sample of English-speaking Twitter accounts. Altogether, our findings suggest that the IRA’s operations were largely unsophisticated and “low-budget” in nature, with no serious attempts at point-of-origin obfuscation being taken.

Disinformation Warfare: Understanding State-Sponsored Trolls on Twitter and Their Influence on the Web

“…active Russian trolls, because 6 days prior to this writing Twitter announced they have discovered over 1K more troll accounts. 2 Nonetheless, it constitutes an invaluable "ground truth" dataset enabling efforts to shed light on the behavior of state-sponsored troll accounts.…”

Twitter trolls: a linguistic profile of anti-democratic discourse

“…This work has used thematic information, sentiment analysis, keyword/n-gram information, and syntactic n-grams (e.g. Boyd et al 2018;Im et al 2019;Ghanem et al 2019). While we have aimed at providing an overview of the linguistic properties of how troll data differ from genuine human accounts, we acknowledge that we simply do not yet have sufficient empirical evidence of the linguistic properties of troll data in English that originates from settings in which English is used as a non-native resource.…”

FacTweet: Profiling Fake News Twitter Accounts

“…Another existing direction in the literature is the detection of online trolls or bots [21]. This is different from our setting, since online trolls are less formal and try to imitate individuals by spreading a mixed content, e.g., social media funneling [6], news, personal opinions [8], etc.. On the other hand, the content of fake news Twitter accounts is formal, objective, and focused on spreading news content only. To the best of our knowledge, this is the first work aiming to detect factuality at account level, specifically from a textual perspective.…”