Discovery, Articulation and Analysis of Communication Framings

ACL ARR 2026 January Submission6963 Authors

Keywords: Framing, Topic Aspects, Communication Frames, Multi-Agent Framework

Abstract: In social media discourse, the framing of a topic dictates the way opinions are formed. This paper presents two multi-agent frameworks: one for discovering what topic aspects are framed, and another for identifying how they are framed. This enables an analysis of a topic's discourse that reveals what framings are dominant while also providing an interpretation of the framings. Experiments across four different topics show promising results for discovering, articulating and analyzing framings, providing a novel understanding of controversial topics.

Paper Type: Long

Research Area: Computational Social Science, Cultural Analytics, and NLP for Social Good

Research Area Keywords: frame detection and analysis, NLP tools for social analysis, quantitative analyses of news and/or social media

Contribution Types: Position papers

Languages Studied: English

Submission Number: 6963