Advanced topic modeling with large language models: analyzing social media content from dementia caregivers
Weiqing He, Bojian Hou, Amy Zheng, Yanbo Feng, Ari Klein, Karen O’Connor, Shu Yang, Tianqi Shang, George Demiris, Graciela Gonzalez-Hernandez, Li Shen, Peter Abadir · 2025
Read Advanced topic modeling with large language models: analyzing social media content from dementia caregivers by Weiqing He, Bojian Hou, Amy Zheng, Yanbo Feng, Ari Klein, Karen O’Connor, Shu Yang, Tianqi Shang, George Demiris, Graciela Gonzalez-Hernandez, Li Shen, Peter Abadir (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12742845.txt.
Description
Weiqing He leads a team of twelve in a 2025 study that uses large language models to mine the posts of dementia caregivers. Classic topic tools often miss meaning and yield muddy themes. Caregiver posts hold rich first-hand strain and wisdom, if the themes can be drawn out cleanly.
The team fed more than 230,000 posts to a chat model in two stages: chunks of a thousand posts each gave first-pass themes, then a second pass merged them. They set the result against 11 older methods, from classic topic models to a transformer-based one. The language model route read the posts with a firmer grip on sense.
Catalog record
| CREATOR | Weiqing He, Bojian Hou, Amy Zheng, Yanbo Feng, Ari Klein, Karen O’Connor, Shu Yang, Tianqi Shang, George Demiris, Graciela Gonzalez-Hernandez, Li Shen, Peter Abadir |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 53 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |