Narrative Media Framing in Political Discourse

2025-05-31

AI Summary

Narrative frameworks—comprising roles, plot structures, and causal chains—in political discourse have long been overlooked by automated framing analysis. Method: This paper introduces the first formalized narrative framing analysis framework, systematically integrating narratological elements into computational framing analysis. It proposes computationally tractable definitions of narrative framing components and combines human annotation, zero- and few-shot LLM predictions, unsupervised topic modeling, and contrastive discourse analysis. Contributions/Results: (1) We release the first annotated dataset of narrative frames in climate discourse; (2) we identify systematic differences in narrative framing usage between left- and right-wing media; (3) we demonstrate strong cross-issue generalizability—validating the framework on both climate change and COVID-19 discourse—with unsupervised outputs aligning closely with established communication theories.

Technology Category

• Natural Language Processing: Discourse, Pragmatics & Argument Mining
• Application Domains: Humanities & Computational Social Science
• Knowledge Representation and Reasoning: Argumentation

Application Category

• Social Networks and Social Media: Media and governance, opinion dynamics, filter bubbles, polarization
• Web Mining and Content Analysis: Sentiment analysis and opinion mining
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling

Abstract

Narrative frames are a powerful way of conceptualizing and communicating complex, controversial ideas, however automated frame analysis to date has mostly overlooked this framing device. In this paper, we connect elements of narrativity with fundamental aspects of framing, and present a framework which formalizes and operationalizes such aspects. We annotate and release a data set of news articles in the climate change domain, analyze the dominance of narrative frame components across political leanings, and test LLMs in their ability to predict narrative frames and their components. Finally, we apply our framework in an unsupervised way to elicit components of narrative framing in a second domain, the COVID-19 crisis, where our predictions are congruent with prior theoretical work showing the generalizability of our approach.

Problem

• Automated frame analysis overlooks narrative framing in discourse
• Formalizing narrativity aspects for framing analysis in political communication
• Testing LLMs to predict narrative frames across political leanings

Innovation

• Connects narrativity with framing aspects
• Formalizes framework for narrative frame analysis
• Tests LLMs in predicting narrative frames