For Whom the Bot Tolls

A Neural Networks Approach to Measuring Political Orientation of Twitter Bots in Russia

Denis Stukal, Sergey Sanovich, Joshua Tucker, Richard Bonneau

Research output: Contribution to journalArticle

Abstract

Computational propaganda and the use of automated accounts in social media have recently become the focus of public attention, with alleged Russian government activities abroad provoking particularly widespread interest. However, even in the Russian domestic context, where anecdotal evidence of state activity online goes back almost a decade, no public systematic attempt has been made to dissect the population of Russian social media bots by their political orientation. We address this gap by developing a deep neural network classifier that separates pro-regime, anti-regime, and neutral Russian Twitter bots. Our method relies on supervised machine learning and a new large set of labeled accounts, rather than externally obtained account affiliations or orientation of elites. We also illustrate the use of our method by applying it to bots operating in Russian political Twitter from 2015 to 2017 and show that both pro- and anti-Kremlin bots had a substantial presence on Twitter.

Original languageEnglish (US)
JournalSAGE Open
Volume9
Issue number2
DOIs
StatePublished - Apr 1 2019

Fingerprint

twitter
political attitude
neural network
Russia
social media
regime
propaganda
elite
learning
evidence
Social Media
Neural Networks
Kremlin
Government
Machine Learning
Computational
Classifier
Elites
Propaganda

Keywords

  • natural language processing
  • neural network
  • propaganda
  • Russia
  • social media
  • Twitter bots

ASJC Scopus subject areas

  • Arts and Humanities(all)
  • Social Sciences(all)

Cite this

For Whom the Bot Tolls : A Neural Networks Approach to Measuring Political Orientation of Twitter Bots in Russia. / Stukal, Denis; Sanovich, Sergey; Tucker, Joshua; Bonneau, Richard.

In: SAGE Open, Vol. 9, No. 2, 01.04.2019.

Research output: Contribution to journalArticle

@article{a09c1f9a6e544e26ae8c912a0c32a270,
title = "For Whom the Bot Tolls: A Neural Networks Approach to Measuring Political Orientation of Twitter Bots in Russia",
abstract = "Computational propaganda and the use of automated accounts in social media have recently become the focus of public attention, with alleged Russian government activities abroad provoking particularly widespread interest. However, even in the Russian domestic context, where anecdotal evidence of state activity online goes back almost a decade, no public systematic attempt has been made to dissect the population of Russian social media bots by their political orientation. We address this gap by developing a deep neural network classifier that separates pro-regime, anti-regime, and neutral Russian Twitter bots. Our method relies on supervised machine learning and a new large set of labeled accounts, rather than externally obtained account affiliations or orientation of elites. We also illustrate the use of our method by applying it to bots operating in Russian political Twitter from 2015 to 2017 and show that both pro- and anti-Kremlin bots had a substantial presence on Twitter.",
keywords = "natural language processing, neural network, propaganda, Russia, social media, Twitter bots",
author = "Denis Stukal and Sergey Sanovich and Joshua Tucker and Richard Bonneau",
year = "2019",
month = "4",
day = "1",
doi = "10.1177/2158244019827715",
language = "English (US)",
volume = "9",
journal = "SAGE Open",
issn = "2158-2440",
publisher = "SAGE Publications Inc.",
number = "2",

}

TY - JOUR

T1 - For Whom the Bot Tolls

T2 - A Neural Networks Approach to Measuring Political Orientation of Twitter Bots in Russia

AU - Stukal, Denis

AU - Sanovich, Sergey

AU - Tucker, Joshua

AU - Bonneau, Richard

PY - 2019/4/1

Y1 - 2019/4/1

N2 - Computational propaganda and the use of automated accounts in social media have recently become the focus of public attention, with alleged Russian government activities abroad provoking particularly widespread interest. However, even in the Russian domestic context, where anecdotal evidence of state activity online goes back almost a decade, no public systematic attempt has been made to dissect the population of Russian social media bots by their political orientation. We address this gap by developing a deep neural network classifier that separates pro-regime, anti-regime, and neutral Russian Twitter bots. Our method relies on supervised machine learning and a new large set of labeled accounts, rather than externally obtained account affiliations or orientation of elites. We also illustrate the use of our method by applying it to bots operating in Russian political Twitter from 2015 to 2017 and show that both pro- and anti-Kremlin bots had a substantial presence on Twitter.

AB - Computational propaganda and the use of automated accounts in social media have recently become the focus of public attention, with alleged Russian government activities abroad provoking particularly widespread interest. However, even in the Russian domestic context, where anecdotal evidence of state activity online goes back almost a decade, no public systematic attempt has been made to dissect the population of Russian social media bots by their political orientation. We address this gap by developing a deep neural network classifier that separates pro-regime, anti-regime, and neutral Russian Twitter bots. Our method relies on supervised machine learning and a new large set of labeled accounts, rather than externally obtained account affiliations or orientation of elites. We also illustrate the use of our method by applying it to bots operating in Russian political Twitter from 2015 to 2017 and show that both pro- and anti-Kremlin bots had a substantial presence on Twitter.

KW - natural language processing

KW - neural network

KW - propaganda

KW - Russia

KW - social media

KW - Twitter bots

UR - http://www.scopus.com/inward/record.url?scp=85064264630&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85064264630&partnerID=8YFLogxK

U2 - 10.1177/2158244019827715

DO - 10.1177/2158244019827715

M3 - Article

VL - 9

JO - SAGE Open

JF - SAGE Open

SN - 2158-2440

IS - 2

ER -