Identifying political topics in social media messages: A lexicon-based approach

Sam Jackson, Feifei Zhang, Olga Boichak, Lauren Bryant, Yingya Li, Jeffrey Hemsley, Jennifer Stromer-Galley, Bryan Semaan, Nancy McCracken

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

In this paper, we introduce a lexicon-based method for identifying political topics in social media messages. After discussing several critical shortcomings of unsupervised topic identification for this task, we describe the lexicon-based approach. We test our lexicon on candidate-generated campaign messages on Facebook and Twitter in the 2016 U.S. presidential election. The results show that this approach provides reliable results for eight of nine political topic categories. In closing, we describe steps to improve our approach and how it can be used for future research on political topics in social media messages.

Original languageEnglish (US)
Title of host publication8th International Conference on Social Media and Society
Subtitle of host publicationSocial Media for Good or Evil, #SMSociety 2017
PublisherAssociation for Computing Machinery
VolumePart F129683
ISBN (Electronic)9781450348478
DOIs
StatePublished - Jul 28 2017
Event8th International International Conference on Social Media and Society, #SMSociety 2017 - Toronto, Canada
Duration: Jul 28 2017Jul 30 2017

Other

Other8th International International Conference on Social Media and Society, #SMSociety 2017
CountryCanada
CityToronto
Period7/28/177/30/17

Keywords

  • Document classification
  • political communication
  • Political issues
  • Presidential campaigns
  • Social media
  • topic identification

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition
  • Software

Cite this