Tweeting to the Target: Candidates’ Use of Strategic Messages and @Mentions on Twitter

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

This paper reports on a mixed-methods (i.e., content analysis, machine learning, and quantitative analysis) study of Twitter use among 74 U.S. gubernatorial candidates during the 2014 election. In extending the theory of controlled interactivity, this article focuses on politicians’ use of the @mention where we detail differing messaging strategies when candidates mention themselves versus their opponents, and between incumbents and challengers. Results suggest that candidates use the @mention feature as a subtle audience targeting mechanism. Our work also offers a methodological contribution by showing that machine-learning models perform better when context variables are included.

Original languageEnglish (US)
Pages (from-to)3-18
Number of pages16
JournalJournal of Information Technology and Politics
Volume15
Issue number1
DOIs
StatePublished - Jan 2 2018

Fingerprint

twitter
Learning systems
candidacy
interactive media
learning
politician
content analysis
election
Chemical analysis

Keywords

  • analysis
  • machine learning
  • political elections
  • strategic messages
  • Twitter

ASJC Scopus subject areas

  • Computer Science(all)
  • Sociology and Political Science
  • Public Administration

Cite this

@article{168ba4e45f844fb3a0806ce2cae27df5,
title = "Tweeting to the Target: Candidates’ Use of Strategic Messages and @Mentions on Twitter",
abstract = "This paper reports on a mixed-methods (i.e., content analysis, machine learning, and quantitative analysis) study of Twitter use among 74 U.S. gubernatorial candidates during the 2014 election. In extending the theory of controlled interactivity, this article focuses on politicians’ use of the @mention where we detail differing messaging strategies when candidates mention themselves versus their opponents, and between incumbents and challengers. Results suggest that candidates use the @mention feature as a subtle audience targeting mechanism. Our work also offers a methodological contribution by showing that machine-learning models perform better when context variables are included.",
keywords = "analysis, machine learning, political elections, strategic messages, Twitter",
author = "Jeffrey Hemsley and Jennifer Stromer-Galley and Bryan Semaan and Sikana Tanupabrungsun",
year = "2018",
month = "1",
day = "2",
doi = "10.1080/19331681.2017.1338634",
language = "English (US)",
volume = "15",
pages = "3--18",
journal = "Journal of Information Technology and Politics",
issn = "1933-1681",
publisher = "Routledge",
number = "1",

}

TY - JOUR

T1 - Tweeting to the Target

T2 - Candidates’ Use of Strategic Messages and @Mentions on Twitter

AU - Hemsley, Jeffrey

AU - Stromer-Galley, Jennifer

AU - Semaan, Bryan

AU - Tanupabrungsun, Sikana

PY - 2018/1/2

Y1 - 2018/1/2

N2 - This paper reports on a mixed-methods (i.e., content analysis, machine learning, and quantitative analysis) study of Twitter use among 74 U.S. gubernatorial candidates during the 2014 election. In extending the theory of controlled interactivity, this article focuses on politicians’ use of the @mention where we detail differing messaging strategies when candidates mention themselves versus their opponents, and between incumbents and challengers. Results suggest that candidates use the @mention feature as a subtle audience targeting mechanism. Our work also offers a methodological contribution by showing that machine-learning models perform better when context variables are included.

AB - This paper reports on a mixed-methods (i.e., content analysis, machine learning, and quantitative analysis) study of Twitter use among 74 U.S. gubernatorial candidates during the 2014 election. In extending the theory of controlled interactivity, this article focuses on politicians’ use of the @mention where we detail differing messaging strategies when candidates mention themselves versus their opponents, and between incumbents and challengers. Results suggest that candidates use the @mention feature as a subtle audience targeting mechanism. Our work also offers a methodological contribution by showing that machine-learning models perform better when context variables are included.

KW - analysis

KW - machine learning

KW - political elections

KW - strategic messages

KW - Twitter

UR - http://www.scopus.com/inward/record.url?scp=85041113019&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85041113019&partnerID=8YFLogxK

U2 - 10.1080/19331681.2017.1338634

DO - 10.1080/19331681.2017.1338634

M3 - Article

AN - SCOPUS:85041113019

VL - 15

SP - 3

EP - 18

JO - Journal of Information Technology and Politics

JF - Journal of Information Technology and Politics

SN - 1933-1681

IS - 1

ER -