SocialMediAI

Understanding the impact of AI and social media interactions on human health

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

  1. 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