Advanced topic modeling with large language models: analyzing social media content from dementia caregivers
This study introduces a novel methodology for applying LLMs to large-scale topic modeling tasks, demonstrating superior performance over traditional and state-of-the-art approaches. The significant improvement in coherence scores suggests that LLMs can better capture the semantic relationships within topics. Our approach addresses key challenges in context length limitations and prompt engineering, while providing more coherent and interpretable insights into caregiver experiences that can inform targeted support strategies.
Authors
- Tianqi Shang (ORCID: https://orcid.org/0009-0007-7147-0316)
- Karen O’Connor
- Shu Yuan Yang (ORCID: https://orcid.org/0000-0002-4709-6551)
- George Demiris (ORCID: https://orcid.org/0000-0002-6318-5829)
- Ari Z Klein (ORCID: https://orcid.org/0000-0002-8281-3464)
- Li Shen (ORCID: https://orcid.org/0000-0001-6520-1418)
- Weiqing He
- Bojian Hou
- Yanbo Feng
- Amy Zheng
- Graciela Gonzalez-Hernandez
Institutions
- Cedars-Sinai Medical Center (US)
- University of Pennsylvania (US)
Publication Details
- Journal
- Innovation in Aging
- Published
- 2025-10-26
- DOI
- https://doi.org/10.1093/geroni/igaf120
- Citations
- 2
- Primary Topic
- Topic Modeling
- Type
- article
- Field-Weighted Citation Impact
- 4.96
Funders
- University of Pennsylvania
- Johns Hopkins University
- National Institutes of Health
- University of Massachusetts Amherst