Health influencer videos assessed for credibility using linked arguments
GRID: Modeling Health Influencer Discourse as Argument Networks for Credibility Assessment
Computation and Language
Summary
Social media health discussions often include influencers sharing different opinions on the same topic. The authors developed GRID, a system that connects claims made in influencer videos with scientific evidence and other related claims across videos to judge how trustworthy the content is. They tested GRID on hundreds of videos checked by experts and found that looking at the bigger conversation helps decide credibility better. They also used GRID to see how credible and less credible influencers use different argument styles.
What this means in practice
- •For social media platforms: Automatically evaluate health influencer videos by linking claims to scientific evidence and related content for better credibility assessment.$Commercial implications: Provides platforms with a tool to flag or highlight trustworthy health information, improving user trust and compliance with content policies.
- •For public health communication teams: Identify prevailing credible and non-credible argumentative styles in health influencer content to tailor better outreach and education strategies.
Authors
Nishanth Sridhar Nakshatri, Eylon Caplan, Dan Goldwasser
Abstract
Health-related discussions on social media are increasingly shaped by influencers who offer diverse, and often competing perspectives on the same issue. Yet, such content is typically evaluated in isolation, without considering the broader discourse in which it appears. We introduce GRID (Grounded Reasoning over Interconnected Discourse), a framework for evaluating influencer content through collective inference over the surrounding discourse. GRID represents each video as an argumentation graph connecting claims to its central message, or takeaway, links related claims and takeaways across videos, grounds claims in scientific evidence, and jointly infers credibility over the resulting network. We evaluate GRID on an end-to-end health-related content validation task using 569 influencer videos grounded in expert assessments. Our results show that accounting for the broader discourse improves influencer content validation. Finally, we use GRID-inferred credibility to demonstrate how argumentative strategies and moral framing differ between low- and high-credibility content.