Dharma, Data and Deception: An LLM-Powered Rhetorical Analysis of Cow-Urine Health Claims on YouTube

2026-04-24

AI Summary

This study investigates culturally specific health misinformation on social media regarding the purported health benefits of cow urine, uncovering the discursive mechanisms through which traditional beliefs and pseudoscientific claims intersect. The authors develop a 14-category rhetorical strategy taxonomy and, for the first time, systematically apply advanced large language models—including GPT-4, GPT-4o, and Gemini 2.5 Pro—to automatically annotate transcripts from 100 YouTube videos, complemented by human evaluation to assess reliability. Findings reveal that proponents predominantly employ efficacy claims and appeals to social consensus, whereas opponents rely more heavily on appeals to authority and direct refutation. Inter-annotator agreement in the human-evaluated subset reached 90.1%, demonstrating the method’s high reproducibility and validity in analyzing culturally sensitive health misinformation.

Technology Category

• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Application Domains: Misinformation & Fake News
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Responsible Web: Mitigating misinformation and disinformation
• Web Mining and Content Analysis: Web data provenance, reliability, and authenticity

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.

Problem

• health misinformation
• cow urine
• YouTube
• cultural discourse
• rhetorical analysis

Innovation

• large language models
• rhetorical analysis
• health misinformation
• computational social science
• persuasive tactics