The DARPA Twitter Bot Challenge

By Venkatramanan Siva Subrahmanian, Amos Azaria, Skylar Durst, Vadim Kagan, Aram Galstyan, Kristina Lerman, Linhong Zhu, Emilio Ferrara, Alessandro Flammini, Filippo Menczer and 12 more. Computer, 2016

408 citations recorded by the source corpus.

From politicians and nation states to terrorist groups, numerous organizations reportedly conduct explicit campaigns to influence opinions on social media, posing a risk to freedom of expression. Thus, there is a need to identify and eliminate "influence bots"--realistic, automated identities that illicitly shape discussions on sites like Twitter and Facebook--before they get too influential.

Subfields: Information Systems, Sociology and Political Science, Signal Processing

View Paper: https://www.semanticscholar.org/paper/1f779bb04bf3510cc8b0fc8f5dba896f5e4e6b95

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Information Systems

In Sociology and Political Science

In Signal Processing

Citations in the corpus

Bots increase exposure to negative and inflammatory content in online social systems (2018, neutral): “A great deal of research aims to address this issue, including our own efforts [1,2] and others’ [3-6].”
Disinformation and social bot operations in the run up to the 2017 French presidential election (2017, background): “A great deal of research aims to address this issue, including our own efforts (Ferrara, et al., 2016; Varol, et al., 2017) and others’ (Messias, et al., 2013; Yang, et al., 2014; Gilani, et al., 2015; Subrahmanian, et al., 2016).”
Analyzing the Digital Traces of Political Manipulation: The 2016 Russian Interference Twitter Campaign (2018, methodology): “Determining whether either human or a bot controls a social media account has proven a very challenging task [26, 51].”
Scalable and Generalizable Social Bot Detection through Data Selection (2019, background): “Malicious bots serve as important instruments for orchestrated, large-scale opinion manipulation campaigns on social media (Ferrara et al. 2016a; Subrahmanian et al. 2016).”
Arming the public with artificial intelligence to counter social bots (2019, methodology): “ will at essentially no cost, human detectors cannot. Later eorts therefore mostly leveraged machine learning methods. Approaches based on supervised machine learning algorithms are the most common (Subrahmanian et al., 2016). Supervised approaches depend and often start with the collection of an ex”
The Brexit Botnet and User-Generated Hyperpartisan News (2019, methodology): “The combination of methods reported in the literature (Subrahmanian et al., 2016; Varol, Ferrara, Davis, Menczer, & Flammini, 2017) allowed us to identify a large group of bots whose accounts had been deactivated by the bot master or blocked/removed by Twitter in the aftermath of the referendum.”
Online Human-Bot Interactions: Detection, Estimation, and Characterization (2017, background): “Wald et al. studied the factors affecting the likelihood of a users being targeted by social bots (Wald et al. 2013).”
Finding and Characterizing Information Warfare Campaigns (2020, background): “In 2015 the Defense Advanced Research Projects Agency (DARPA) sponsored a Twitter bot detection competition that was titled “The Twitter Bot Challenge” [226].”
The spread of low-credibility content by social bots (2017, neutral): “For example, our lab and others are developing machine learning algorithms to detect social bots [14, 51, 54].”
Deep Neural Networks for Bot Detection (2018, methodology): “Reports of online manipulation mediated by bots span political conversation [6, 21, 31, 40, 59], fake news [19, 50], conspiracy theories [53], stock market manipulation [18], public health [12], and more [27] — it is worth noting that in some rare occasions bots have been used to deliver positive…”
False Information on Web and Social Media: A Survey (2018, methodology): “[97] found that some bot accounts that spread false information are close to each other and appear as groups in Twitter’s follower-followee network, with significant overlap between their followers and followees.”
BotOrNot: A System to Evaluate Social Bots (2016, background): “Recenly DARPA organized a bot detection challenge to developed techniques for early detection of malicious organized activities [5].”
Characterizing the 2016 Russian IRA influence campaign (2018, methodology): “ center as well. 3.3 Bot Detection Determining whether either a human or a bot controls a social media account has proven a very challenging task Ferrara et al. (2016b); Kudugunta and Ferrara (2018); Subrahmanian et al. (2016). We use 5 We use the algorithm in the Python version of the Igraph librar”
Combating Fake News (2019, background): “[108] found a significant overlap between follower and followees of bot accounts that spread false information, which helps to engineer virality and credibility of posts and inflate the social status of the bot accounts.”
The rise of social bots (2014, background): “lenge, which took place in the spring of 2015, can be effective catalysts of this emerging area of inquiry.(32) Bot behaviors are already quite so-”