Deep neural networks for bot detection

This is why we can't have nice things

With people moving out of physical public spaces due to containment measures to tackle the novel coronavirus (COVID-19) pandemic, online platforms become even more prominent tools to understand social discussion. Studying social media can be informative to assess how we are collectively coping with this unprecedented global crisis. However, social media platforms are also populated by bots, automated accounts that can amplify certain topics of discussion at the expense of others. In this paper, we study 43.3M English tweets about COVID-19 and provide early evidence of the use of bots to promote political conspiracies in the United States, in stark contrast with humans who focus on public health concerns.

What types of COVID-19 conspiracies are populated by Twitter bots?

Background: False claims about COVID-19 vaccines can undermine public trust in ongoing vaccination campaigns, posing a threat to global public health. Misinformation originating from various sources has been spreading on the web since the beginning of the COVID-19 pandemic. Antivaccine activists have also begun to use platforms such as Twitter to promote their views. To properly understand the phenomenon of vaccine hesitancy through the lens of social media, it is of great importance to gather the relevant data.
Objective: In this paper, we describe a data set of Twitter posts and Twitter accounts that publicly exhibit a strong antivaccine stance. The data set is made available to the research community via our AvaxTweets data set GitHub repository. We characterize the collected accounts in terms of prominent hashtags, shared news sources, and most likely political leaning.
Methods: We started the ongoing data collection on October 18, 2020, leveraging the Twitter streaming application programming interface (API) to follow a set of specific antivaccine-related keywords. Then, we collected the historical tweets of the set of accounts that engaged in spreading antivaccination narratives between October 2020 and December 2020, leveraging the Academic Track Twitter API. The political leaning of the accounts was estimated by measuring the political bias of the media outlets they shared.
Results: We gathered two curated Twitter data collections and made them publicly available: (1) a streaming keyword–centered data collection with more than 1.8 million tweets, and (2) a historical account–level data collection with more than 135 million tweets. The accounts engaged in the antivaccination narratives lean to the right (conservative) direction of the political spectrum. The vaccine hesitancy is fueled by misinformation originating from websites with already questionable credibility.
Conclusions: The vaccine-related misinformation on social media may exacerbate the levels of vaccine hesitancy, hampering progress toward vaccine-induced herd immunity, and could potentially increase the number of infections related to new COVID-19 variants. For these reasons, understanding vaccine hesitancy through the lens of social media is of paramount importance. Because data access is the first obstacle to attain this goal, we published a data set that can be used in studying antivaccine misinformation on social media and enable a better understanding of vaccine hesitancy.

COVID-19 Vaccine Hesitancy on Social Media: Building a Public Twitter Dataset of Anti-vaccine Content, Vaccine Misinformation and Conspiracies.

Efficient and reliable social bot classification is crucial for detecting information manipulation on social media. Despite rapid development, state-of-the-art bot detection models still face generalization and scalability challenges, which greatly limit their applications. In this paper we propose a framework that uses minimal account metadata, enabling efficient analysis that scales up to handle the full stream of public tweets of Twitter in real time. To ensure model accuracy, we build a rich collection of labeled datasets for training and validation. We deploy a strict validation system so that model performance on unseen datasets is also optimized, in addition to traditional cross-validation. We find that strategically selecting a subset of training data yields better model accuracy and generalization than exhaustively training on all available data. Thanks to the simplicity of the proposed model, its logic can be interpreted to provide insights into social bot characteristics.

/pdf/scalable-and-generalizable-social-bot-detection-through-data-3mvve34k1m.pdf

Scalable and Generalizable Social Bot Detection through Data Selection.

Until recently, social media was seen to promote democratic discourse on social and political issues. However, this powerful communication platform has come under scrutiny for allowing hostile actors to exploit online discussions in an attempt to manipulate public opinion. A case in point is the ongoing U.S. Congress investigation of Russian interference in the 2016 U.S. election campaign, with Russia accused of, among other things, using trolls (malicious accounts created for the purpose of manipulation) and bots (automated accounts) to spread misinformation and politically biased information. In this study, we explore the effects of this manipulation campaign, taking a closer look at users who re-shared the posts produced on Twitter by the Russian troll accounts publicly disclosed by U.S. Congress investigation. We collected a dataset with over 43 million elections-related posts shared on Twitter between September 16 and November 9, 2016 by about 5.7 million distinct users. This dataset includes accounts associated with the identified Russian trolls. We use label propagation to infer the users' ideology based on the news sources they shared, to classify a large number of them as liberal or conservative with precision and recall above 90%. Conservatives retweeted Russian trolls significantly more often than liberals and produced 36 times more tweets. Additionally, most of the troll content originated in, and was shared by users from Southern states. Using state-of-the-art bot detection techniques, we estimated that about 4.9% and 6.2% of liberal and conservative users respectively were bots. Text analysis on the content shared by trolls reveals that they had a mostly conservative, pro-Trump agenda. Although an ideologically broad swath of Twitter users were exposed to Russian trolls in the period leading up to the 2016 U.S. Presidential election, it was mainly conservatives who helped amplify their message.

Analyzing the digital traces of political manipulation: the 2016 russian interference Twitter campaign

Until recently, social media was seen to promote democratic discourse on social and political issues However, this powerful communication platform has come under scrutiny for allowing hostile actors to exploit online discussions in an attempt to manipulate public opinion A case in point is the ongoing US Congress' investigation of Russian interference in the 2016 US election campaign, with Russia accused of using trolls (malicious accounts created to manipulate) and bots to spread misinformation and politically biased information In this study, we explore the effects of this manipulation campaign, taking a closer look at users who re-shared the posts produced on Twitter by the Russian troll accounts publicly disclosed by US Congress investigation We collected a dataset with over 43 million election-related posts shared on Twitter between September 16 and October 21, 2016, by about 57 million distinct users This dataset included accounts associated with the identified Russian trolls We use label propagation to infer the ideology of all users based on the news sources they shared This method enables us to classify a large number of users as liberal or conservative with precision and recall above 90% Conservatives retweeted Russian trolls about 31 times more often than liberals and produced 36x more tweets Additionally, most retweets of troll content originated from two Southern states: Tennessee and Texas Using state-of-the-art bot detection techniques, we estimated that about 49% and 62% of liberal and conservative users respectively were bots Text analysis on the content shared by trolls reveals that they had a mostly conservative, pro-Trump agenda Although an ideologically broad swath of Twitter users was exposed to Russian Trolls in the period leading up to the 2016 US Presidential election, it was mainly conservatives who helped amplify their message

Analyzing the Digital Traces of Political Manipulation: The 2016 Russian Interference Twitter Campaign

Social media, once hailed as a vehicle for democratization and the promotion of positive social change across the globe, are under attack for becoming a tool of political manipulation and spread of disinformation. A case in point is the alleged use of trolls by Russia to spread malicious content in Western elections. This paper examines the Russian interference campaign in the 2016 US presidential election on Twitter. Our aim is twofold: first, we test whether predicting users who spread trolls’ content is feasible in order to gain insight on how to contain their influence in the future; second, we identify features that are most predictive of users who either intentionally or unintentionally play a vital role in spreading this malicious content. We collected a dataset with over 43 million election-related posts shared on Twitter between September 16 and November 9, 2016, by about 5.7 million users. This dataset includes accounts associated with the Russian trolls identified by the US Congress. Proposed models are able to very accurately identify users who spread the trolls’ content (average AUC score of 96%, using 10-fold validation). We show that political ideology, bot likelihood scores, and some activity-related account meta data are the most predictive features of whether a user spreads trolls’ content or not.

Who Falls for Online Political Manipulation

Recent research brought awareness of the issue of bots on social media and the significant risks of mass manipulation of public opinion in the context of political discussion. In this work, we leverage Twitter to study the discourse during the 2018 US midterm elections and analyze social bot activity and interactions with humans. We collected 2.6 million tweets for 42 days around the election day from nearly 1 million users. We use the collected tweets to answer three research questions: (i) Do social bots lean and behave according to a political ideology? (ii) Can we observe different strategies among liberal and conservative bots? (iii) How effective are bot strategies in engaging humans? We show that social bots can be accurately classified according to their political leaning and behave accordingly. Conservative bots share most of the topics of discussion with their human counterparts, while liberal bots show less overlap and a more inflammatory attitude. We studied bot interactions with humans and observed different strategies. Finally, we measured bots embeddedness in the social network and the extent of human engagement with each group of bots. Results show that conservative bots are more deeply embedded in the social network and more effective than liberal bots at exerting influence on humans.

/pdf/red-bots-do-it-better-comparative-analysis-of-social-bot-2cgewjyyln.pdf

Red Bots Do It Better:Comparative Analysis of Social Bot Partisan Behavior

Until recently, social media were seen to promote democratic discourse on social and political issues. However, this powerful communication ecosystem has come under scrutiny for allowing hostile actors to exploit online discussions in an attempt to manipulate public opinion. A case in point is the ongoing U.S. Congress investigation of Russian interference in the 2016 U.S. election campaign, with Russia accused of, among other things, using trolls (malicious accounts created for the purpose of manipulation) and bots (automated accounts) to spread propaganda and politically biased information. In this study, we explore the effects of this manipulation campaign, taking a closer look at users who re-shared the posts produced on Twitter by the Russian troll accounts publicly disclosed by U.S. Congress investigation. We collected a dataset of 13 million election-related posts shared on Twitter in the year of 2016 by over a million distinct users. This dataset includes accounts associated with the identified Russian trolls as well as users sharing posts in the same time period on a variety of topics around the 2016 elections. We use label propagation to infer the users’ ideology based on the news sources they share. We are able to classify a large number of the users as liberal or conservative with precision and recall above 84%. Conservative users who retweet Russian trolls produced significantly more tweets than liberal ones, about 8 times as many in terms of tweets. Additionally, trolls’ position in the retweet network is stable overtime, unlike users who retweet them who form the core of the election-related retweet network by the end of 2016. Using state-of-the-art bot detection techniques, we estimate that about 5% and 11% of liberal and conservative users are bots, respectively. Text analysis on the content shared by trolls reveal that conservative trolls talk about refugees, terrorism, and Islam, while liberal trolls talk more about school shootings and the police. Although an ideologically broad swath of Twitter users were exposed to Russian trolls in the period leading up to the 2016 U.S. Presidential election, it is mainly conservatives who help amplify their message.

Adam Badawy

Papers

Analyzing the digital traces of political manipulation: the 2016 russian interference Twitter campaign

Analyzing the Digital Traces of Political Manipulation: The 2016 Russian Interference Twitter Campaign

Who Falls for Online Political Manipulation

Red Bots Do It Better:Comparative Analysis of Social Bot Partisan Behavior

Characterizing the 2016 Russian IRA influence campaign