We study the complex interplay between human health and help-seeking or information-seeking behaviours via large language models and social media.
In particular, we are interested in how LLMs can be applied to support under-served populations and conditions in the context of women’s health and the gender health gap.
For example, we developed a pipeline to apply LLMs to extract discussions from relevant content on social media and conduct thematic analysis to explore help-seeking and information-seeking behaviour around women’s health including perceived experiences and barriers.
We are also interested in monitoring and mitigating the complex problem of health misinformation on social media and in LLMs, and developing methods to mitigate misinformation and safeguard LLMs for health.
2025
-
Large Language Models Reveal Menstruation Experiences and Needs on Social Media
Charlotte Tumescheit, Davinny Sou, Marcia Nißen, Tobias Kowatsch, and Janna Hastings
Studies in Health Technology and Informatics, 2025
The gender knowledge gap in medicine, particularly regarding menstruation and disorders such as endometriosis, often results in delayed diagnoses and inadequate care. Many menstruating individuals report dismissal of debilitating symptoms, driving them to seek information and support on online platforms such as TikTok and YouTube. This study leverages social media to identify key topics reflecting lived experiences and needs to bridge this knowledge gap. Using a novel pipeline, we analysed video comments using BERTopic and the Llama 3.1 model. Key topics, including emotional support, educational guidance, and community validation, were consistent with prior research. This study underscores the potential of social media and large language models to inform inclusive menstrual health research, revealing unique insights regarding the menstruation experiences and needs of underrepresented and historically overlooked individuals such as those with irregular cycles.