Dharma, Data and Deception: An LLM-Powered Rhetorical Analysis of Cow-Urine Health Claims on YouTube
Sheza Munir, Ratna Kandala, Anamta Khan, Deepti, Joyojeet Pal
TLDR
LLMs analyze YouTube transcripts on cow urine health claims, revealing distinct rhetorical strategies used by promoters and debunkers.
Key contributions
- Analyzed 100 YouTube transcripts on cow urine health claims using LLMs.
- Developed a 14-category taxonomy of persuasive tactics for misinformation.
- Found promoters use efficacy/social proof; debunkers use authority/rebuttal.
- Achieved 90.1% human agreement on LLM annotations, validating the method.
Why it matters
This paper advances computational methods for misinformation analysis, especially in culturally specific contexts. It demonstrates LLMs' utility in large-scale studies of online discourse, offering a robust framework for understanding health misinformation.
Original Abstract
Health misinformation remains one of the most pressing challenges on social media, particularly when cultural traditions intersect with scientific-sounding claims. These dynamics are not only global but also deeply local, manifesting in culturally specific controversies that require careful analysis. Motivated by this, we examine 100 YouTube transcripts that promote or debunk cow urine (gomutra) as a health remedy, focusing on rhetorical strategies such as appeals to authority, efficacy appeals, and conspiracy framing. We employ large language models (LLMs) including GPT-4, GPT-4o, GPT-4.1, GPT-5, Gemini 2.5 Pro, and Mistral Medium 3 to annotate transcripts using a 14-category taxonomy of persuasive tactics. Our analysis reveals that promoters predominantly rely on efficacy appeals and social proof, while debunkers emphasize authority and rebuttal. Human evaluation of a subset of annotations yielded 90.1\% inter-annotator agreement, confirming the reliability of our taxonomy and validation process. This work advances computational methods for misinformation analysis and demonstrates how LLMs can support large-scale studies of cultural discourse online.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.