Brexit and bots: characterizing the behaviour of automated accounts on Twitter during the UK election

TL;DR

This study investigates how automated accounts shaped Brexit-related discourse on Twitter during the 2019 UK general election. It combines Botometer-based bot detection with statistically validated network projections, discursive-community analysis, and core-periphery metrics to quantify bot presence, timing, and narrative strategies. The authors find a pronounced influx of bots in the days leading up to the election, with novel bot behavior emerging after a TV debate, and show that bots and suspended accounts participate across multiple communities and topics, including Trump-related narratives. Together, these findings illuminate how automated activity can amplify political topics, affect online discourse, and interact with platform governance implications in electoral contexts.

Abstract

Online Social Networks represent a novel opportunity for political campaigns, revolutionising the paradigm of political communication. Nevertheless, many studies uncovered the presence of d/misinformation campaigns or of malicious activities by genuine or automated users, putting at severe risk the credibility of online platforms. This phenomenon is particularly evident during crucial political events, as political elections. In the present paper, we provide a comprehensive description of the structure of the networks of interactions among users and bots during the UK elections of 2019. In particular, we focus on the polarised discussion about Brexit on Twitter analysing a data set made of more than 10 million tweets posted for over a month. We found that the presence of automated accounts fostered the debate particularly in the days before the UK national elections, in which we find a steep increase of bots in the discussion; in the days after the election day, their incidence returned to values similar to the ones observed few weeks before the elections. On the other hand, we found that the number of suspended users (i.e. accounts that were removed by the platform for some violation of the Twitter policy) remained constant until the election day, after which it reached significantly higher values. Remarkably, after the TV debate between Boris Johnson and Jeremy Corbyn, we observed the injection of a large number of novel bots whose behaviour is markedly different from that of pre-existing ones. Finally, we explored the bots' stance, finding that their activity is spread across the whole political spectrum, although in different proportions, and we studied the different usage of hashtags by automated accounts and suspended users, thus targeting the formation of common narratives in different sides of the debate.

Figures (13)

• Figure 1: Monopartite backbone extraction from a bipartite network. The bipartite network of the first panel is projected on both layers. After the two one-mode projections are obtained (second panel), the original links can be added again to obtain the backbone of the network (third panel), that will highlight mixed groups of interactions.
• Figure 2: Number of tweets (including retweets) and users per day. The peak on the 12th of December that can be observed in both panels is in concurrence of the day of the elections.
• Figure 3: Presence of bots and suspended users in the discussion over time. For users labeled as bots (with a score higher than 0.43) that have not been suspended, there is a change after the debate of the 6th of November (top left), with new bots coming into the discussion (top right). The new bots seem less active than the old ones (bottom). The percentage of bots among genuine users becomes as high as 10%. Among the removed users, the changes happen after the 12th of December (election day), with new suspended users entering the discussion while being less active on average.
• Figure 4: A phase diagram of the core-periphery scores with different colors for bots, suspended users and humans, for the network of retweets among users the day before the election. The histograms on the bottom and left of the phase diagram show the marginal distributions. While automated accounts are concentrated on lower values of presence and participation scores, suspended and genuine users have a flatter distribution, even if a peak on the lower values is still present. Bots are more inclined to retweet accounts in their community (participation score) and moreover focus their activity on few users (relevance score).
• Figure 5: Average scores of participation and presence (top) by category and the KS tests' statistics comparing the distributions (bottom). It is striking the change of behaviour of bots after the election day in both the presence and participation score: in fact, the average values of the scores are almost always higher for bots than for suspended users after the 12th of December. At the same time, the relevance score of suspended accounts is always higher than average users before the election day, dropping to much lower levels after the elections. The p-values of the KS tests are close to 0 during the respective peaks of the KS statistics, and almost always very small in the case of the bots (the maximum bots' p-value is $2\cdot 10^{-2}$).