Detecting Bots on Russian Political Twitter

Denis Stukal, Sergey Sanovich, Richard Bonneau, Joshua Tucker

Research output: Contribution to journalArticle

Abstract

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.

Original languageEnglish (US)
Pages (from-to)310-324
Number of pages15
JournalBig Data
Volume5
Issue number4
DOIs
StatePublished - Dec 1 2017

Fingerprint

Classifiers
Twitter

Keywords

  • bot detection
  • ensemble methods
  • machine learning
  • Russia
  • Twitter

ASJC Scopus subject areas

  • Information Systems
  • Computer Science Applications
  • Information Systems and Management

Cite this

Detecting Bots on Russian Political Twitter. / Stukal, Denis; Sanovich, Sergey; Bonneau, Richard; Tucker, Joshua.

In: Big Data, Vol. 5, No. 4, 01.12.2017, p. 310-324.

Research output: Contribution to journalArticle

Stukal, D, Sanovich, S, Bonneau, R & Tucker, J 2017, 'Detecting Bots on Russian Political Twitter', Big Data, vol. 5, no. 4, pp. 310-324. https://doi.org/10.1089/big.2017.0038
Stukal, Denis ; Sanovich, Sergey ; Bonneau, Richard ; Tucker, Joshua. / Detecting Bots on Russian Political Twitter. In: Big Data. 2017 ; Vol. 5, No. 4. pp. 310-324.
@article{ce7f3ce1a1634dcc9aae5f83cec06a2b,
title = "Detecting Bots on Russian Political Twitter",
abstract = "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.",
keywords = "bot detection, ensemble methods, machine learning, Russia, Twitter",
author = "Denis Stukal and Sergey Sanovich and Richard Bonneau and Joshua Tucker",
year = "2017",
month = "12",
day = "1",
doi = "10.1089/big.2017.0038",
language = "English (US)",
volume = "5",
pages = "310--324",
journal = "Big Data",
issn = "2167-6461",
publisher = "Mary Ann Liebert Inc.",
number = "4",

}

TY - JOUR

T1 - Detecting Bots on Russian Political Twitter

AU - Stukal, Denis

AU - Sanovich, Sergey

AU - Bonneau, Richard

AU - Tucker, Joshua

PY - 2017/12/1

Y1 - 2017/12/1

N2 - 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.

AB - 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.

KW - bot detection

KW - ensemble methods

KW - machine learning

KW - Russia

KW - Twitter

UR - http://www.scopus.com/inward/record.url?scp=85042548167&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85042548167&partnerID=8YFLogxK

U2 - 10.1089/big.2017.0038

DO - 10.1089/big.2017.0038

M3 - Article

VL - 5

SP - 310

EP - 324

JO - Big Data

JF - Big Data

SN - 2167-6461

IS - 4

ER -