Logo Lanfrica
  • Accueil
  • Atlas
  • Analyses
  • Documentation
  • Sign in

© 2026 Lanfrica. Tous droits réservés. Tous les droits d'auteur des ressources affichées sur le site Web Lanfrica appartiennent aux détenteurs de droits d'auteur d'origine, sauf indication contraire explicite.

The Effectiveness of Narrative Structure at Building Public Support

Domaine:

natural language processing
Créateur:
Pal
Éditeur:
Cen
Éditeur:
OSF
Hôte:avatar
As many countries note declining trust in government institutions, the academic and public focus is largely on the relationship with government performance. While some existing work points to this being a tenuous connection, there has been minimal attention paid to other methods of persuasion. In this project, I explore one of the ways governments and leaders seek to shift public perceptions: storytelling. I use the case of the main investigative service in Kenya, the Directorate of Criminal Investigations, which has been sharing true stories of their cases on Twitter as a way to build trust in the police. Using sentiment classification, I show that following these stories causes people to write more positively about the police. I also build on burgeoning methods for story modeling and generation to test whether adhering to a classic story structure makes these narratives more persuasive. This project aims to contribute to our understanding of how trust develops and whether structure of communication as well as content matters.

Visit

doi.orgosf.io

Tasks

sentiment analysistext classification

Tags

Political ScienceFOS: Political scienceSocial and Behavioral Sciences

Licenses

Creative Commons Attribution 4.0 Internationalhttps://creativecommons.org/licenses/by/4.0/legalcode