Anamta Khan

Anamta Khan, Ratna Kandala, Deepti et al.

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-V3.1), 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.

Sheza Munir, Ratna Kandala, Anamta Khan et al.

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.

Anamta Khan

Unmanned Aerial Vehicles (UAVs), in particular Drones, have gained significant importance in diverse sectors, mainly military uses. Recently, we can see a growth in acceptance of autonomous UAVs in civilian spaces as well. However, there is still a long way to go before drones are capable enough to be safely used without human surveillance. A lot of subsystems and components are involved in taking care of position estimation, route planning, software/data security, and collision avoidance to have autonomous drones that fly in civilian spaces without being harmful to themselves, other UAVs, environment, or humans. The ultimate goal of this research is to advance collision avoidance and mitigation techniques through quantitative safety risk assessment. To this end, it is required to identify the most relevant faults/failures/threats that can happen during a drone's flight/mission. The analysis of historical data is also a relevant instrument to help to characterize the most frequent and relevant issues in UAV systems, which may cause safety hazards. Then we need to estimate their impact quantitatively, by using fault injection techniques. Knowing the growing interests in UAVs and their huge potential for future commercial applications, the expected outcome of this work will be helpful to researchers for future related research studies. Furthermore, we envisage the utilization of expected results by companies to develop safer drone applications, and by air traffic controllers for building failure prediction and collision avoidance solutions.