Champions for Social Good: How can we Discover Social Sentiment and Attitude-driven Patterns in Prosocial Communication?

Research output: Contribution to journalJournal articleResearchpeer-review

20 Downloads (Pure)

Abstract

The UN High Commissioner on Refugees pursues a social media strategy to inform people about displaced populations and refugee emergencies. It actively engages public figures so its prosocial communications can promote greater awareness. This improves social informedness and support for policy changes in its services. We study social media champions’ Twitter communications and roles as high-profile influencers. We offer a design science research and data analytics framework and propositions based on social informedness theory to assess communication about the UNHCR’s mission. Two variables, refugee-emergency and champion type, relate to UNHCR champions’ followers’ informedness. Based on a Twitter sentiment and attitude corpus, we apply a five-step design science analytics framework involving machine learning and natural language processing to test emergency type and champion influencer impacts on patterns observed in social communication. Positive and neutral sentiment dominated the champions’ and their followers’ tweets for most refugee-emergency types. High participation-intensity champions emphasized high-intensity emergencies with dominant positive or neutral sentiment and sharing or liking attitude tweet patterns. Sports figures with millions of their followers’ effects were limited in spreading UNHCR’s message. We demonstrate the power of data science for prosocial policy based on refugee crisis awareness and instantiate our methods and knowledge contributions in a research framework deriving knowledge, decisions and actions based on behavioral, design and economics of information systems (IS) perspectives.
Original languageEnglish
JournalJournal of the Association for Information Systems
Volume24
Issue number6
Pages (from-to)1562-1593
Number of pages32
ISSN1558-3457
DOIs
Publication statusPublished - Nov 2023

Bibliographical note

Published online: 16 Feb 2023.

Keywords

  • Data science for social good
  • Deep learning
  • Influencers
  • Machine learning
  • Natrual language processing
  • Prosocial behavior
  • Sentiment analytics
  • Social outreach
  • Theory of social informedness
  • Twitter

Cite this