The rise of semi-automatic Twitter bots gained public attention following the 2016 presidential election, and to better understand how they operate, we design a methodology for detecting them in the Twittersphere. We find that a primary use of bots in Russia from 2014 to 2015 was to manipulate search rankings.
Stukal, Denis, Sergey Sanovich, Richard Bonneau, and Joshua A. Tucker. “Detecting Bots on Russian Political Twitter.” Big Data 5, no. 4 (2017): 310–24. https://doi.org/10.1089/big.2017.0038
Dec 01, 2017
Area of Study
Automated and semiautomated Twitter accounts, bots, have recently gained significant public attention due to their potential interference in the political realm. In this study, we develop a methodology for detecting bots on Twitter using an ensemble of classifiers and apply it to study bot activity within political discussions in the Russian Twittersphere. We focus on the interval from February 2014 to December 2015, an especially consequential period in Russian politics. Among accounts actively Tweeting about Russian politics, we find that on the majority of days, the proportion of Tweets produced by bots exceeds 50%. We reveal bot characteristics that distinguish them from humans in this corpus, and find that the software platform used for Tweeting is among the best predictors of bots. Finally, we find suggestive evidence that one prominent activity that bots were involved in on Russian political Twitter is the spread of news stories and promotion of media who produce them.
Social media accounts whose content is generated by a computer program, rather than a human being (called bots), can be particularly detrimental to the social media ecology as meaningful discussion between peers can easily fade in the presence of artificially boosted stories and opinions. Recently, automated and semi automated Twitter bots gained public attention after their potential interference in politics abroad.
In this study, we develop a methodology for detecting bots on Twitter using a series of classifiers, which we then apply to study bot activity within political discussions in the Russian Twittersphere, focusing on an especially consequential period in Russian politics from February 2014 to December 2015. Among accounts actively tweeting about Russian politics, we find that the majority of tweets (more than 50 percent) were produced by bots.
We find evidence that bots are prominently involved in Russian political Twitter for the spread of news stories and promotion of media who produce them. Bots represent a very large portion of the Russian political Twittersphere, but most bots in our collection do not tweet much more often than humans (at least about politics), and that the most common use of bots was to share news headlines, although not necessarily links to the news stories. This in turn suggests the possibility that a primary use of bots in Russia from 2014 to 2015 was to manipulate search rankings.