The Brexit Botnet and User-Generated Hyperpartisan News

Abstract

This is the accepted version of the paper.This version of the publication may differ from the final published version. Permanent repository link: AbstractIn this paper we uncover a network of Twitterbots comprising 13,493 accounts that tweeted the U.K. E.U. membership referendum, only to disappear from Twitter shortly after the ballot. We compare active users to this set of political bots with respect to temporal tweeting behavior, the size and speed of retweet cascades, and the composition of their retweet cascades (user-to-bot vs.bot-to-bot) to evidence strategies for bot deployment. Our results move forward the analysis of political bots by showing that Twitterbots can be effective at rapidly generating small to medium-sized cascades; that the retweeted content comprises user-generated hyperpartisan news, which is not strictly fake news, but whose shelf life is remarkably short; and, finally, that a botnet may be organized in specialized tiers or clusters dedicated to replicating either active users or content generated by other bots.

A network topology approach to bot classification

“…Botometer, the first publicly available classifier, uses a random forest ensemble supervised learning method [9]. 3 The classifier uses multiple features from the user's network, user profile, friends, temporal features, content and sentiment. The exact implementation is not publicly available, but Gilani et al [21] attempted a reproduction and extension to the work of Davis et al [9] and made the methodology and data open access.…”

“…Echeverría and Zhou [11] offer a brief overview of such 'threatening' bot activities on Twitter: spamming, fake trending topics, opinion manipulation, astroturfing 1 , fake followers and API contamination. The most notorious example in recent memory of such activities was with the British referendum on European Union membership, 2 where both sides of the debate included bot activities [3]. Another is the 2016 US Presidential election [30].…”

Deploying South African social honeypots on Twitter

“…A list of trending keywords and key phrases was generated from the 44 political leaders, based on their activity in the previous week. 1 These keywords and key phrases were ranked based on their popularity amongst the users. We then used these keywords to identify six additional techniques based on interacting with the list sequentially or in a random fashion.…”

“…Howard and Kollanyi [4] discovered that up to 32% of the conversation on Twitter, involving the referendum, may have been driven by political bots. Bastos and Mercea [1] investigated the role of these political bots in sharing partisan and inaccurate news. In a review of the data of the referendum, Narayanan et al [11] suggests evidence of involvement from Russian borne actors in the creation of political bots.…”

Investigating Italian disinformation spreading on Twitter in the context of 2019 European elections

“…As people is more and more suspicious towards traditional media coverage, news consumption has considerably shifted towards online social media; these exhibit unique characteristics which favored, among other things, the proliferation of low-credibility content and malicious information [1,2]. Consequently, it has been questioned in many circumstances whether and to what extent disinformation news circulating on social platforms impacted on the outcomes of political votes [2][3][4][5].…”