Milking the Metaphors: Cultural Obfuscation in Wellness (COW) around Gomutra on YouTube using LLMs

Anamta Khan, Ratna Kandala, Deepti, Sheza Munir, Joyojeet Pal

Keywords: health misinformation, cultural obfuscation, traditional medicine, YouTube, discourse analysis, large language models, prompt sensitivity, gendered rhetoric, Indic languages, gomutra, non-Western NLP, culturally embedded misinformation

TL;DR: Cultural Obfuscation in Wellness (COW) around Gomutra on YouTube using LLMs

Abstract: Social media platforms have become primary channels for health information in the Global South. Using gomutra (cow urine) discourse on YouTube in India as a case study, we present a post-facto Large Language Model(LLM)-assisted discourse analysis of 30 multilingual transcripts showing that promotional content blends sacred traditional language with pseudo-scientific claims in ways that sophisticated debunking content itself mirrors, creating a rhetorical register that LLMs, trained predominantly on Western corpora, are systematically ill-equipped to analyse. Varying prompt tone across three LLMs (GPT-4o, Gemini 2.5 Pro, DeepSeek), we find that culturally embedded health misinformation does not look like ordinary misinformation, and this cultural obfuscation extends to gendered rhetoric and prompt design, compounding analytical unreliability. Our findings argue that cultural competency in LLM-assisted discourse analysis cannot be retrofitted through prompt engineering alone.

Paper Format Check: Yes

Submission Type: Long Paper (non-archival)

Attendance: I plan to present virtually (only for unavoidable circumstances such as visa issues)

Presenter Name: Deepti

Presenter Email: [e-mail]

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 9