Structured Claim-Level Discourse Representations for Dense Health Narratives
Researchers propose a claim-level discourse framework for health videos, finding 13.22 atomic claims per minute and that LLMs struggle with pragmatic profiling.
The paper introduces a structured framework for claim-level discourse analysis in dense health narratives on social media videos, modeling tuples that link atomic claims with thematic aspects, stance, and multidimensional pragmatic attributes. Analysis found an average of 13.22 atomic claims per minute in health video discourse. A benchmark spanning four health domains with 1,191 manually annotated claims from 60 videos shows current LLMs perform strongly on thematic categorization and stance prediction but struggle with high-dimensional pragmatic profiling, suggesting future systems need task decomposition and specialized inference strategies.
- Health videos average 13.22 atomic claims per minute
- Benchmark includes 1,191 annotated claims from 60 videos across four health domains
- LLMs are strong on thematic categorization and stance prediction
- High-dimensional pragmatic profiling remains a weakness for current LLMs
From the original article
1 min read at arxiv.orgHealth discourse in social media videos often contains densely entangled claims spanning multiple thematic aspects, stances, evidential frames, and rhetorical functions within short conversational spans. Existing approaches largely rely on coarse topic-level, sentiment-based, or stance-oriented representations that do not adequately capture this structure. Our analysis identifies an average of 13.
By Farnoushsadat Nilizadeh · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.