Published on in Vol 4 (2024)

Preprints (earlier versions) of this paper are available at https://preprints.jmir.org/preprint/59641, first published .
Large Language Models Can Enable Inductive Thematic Analysis of a Social Media Corpus in a Single Prompt: Human Validation Study

Large Language Models Can Enable Inductive Thematic Analysis of a Social Media Corpus in a Single Prompt: Human Validation Study

Large Language Models Can Enable Inductive Thematic Analysis of a Social Media Corpus in a Single Prompt: Human Validation Study

Michael S Deiner   1 * , PhD ;   Vlad Honcharov   2, 3 * , MPH ;   Jiawei Li   4 , MS ;   Tim K Mackey   4, 5 , MAS, PhD ;   Travis C Porco   6 , MPH, PhD ;   Urmimala Sarkar   2, 3 , MPH, MD

1 Department of Ophthalmology and Francis I Proctor Foundation, University of California San Francisco, San Francisco, CA, United States

2 Center for Vulnerable Populations, Zuckerberg San Francisco General Hospital, Department of Medicine, University of California San Francisco, San Francisco, CA, United States

3 Division of General Internal Medicine, Zuckerberg San Francisco General Hospital, Department of Medicine, University of California San Francisco, San Francisco, CA, United States

4 S-3 Research, LLC, San Diego, CA, United States

5 Global Health Program, Department of Anthropology, University of California San Diego, La Jolla, CA, United States

6 Departments of Ophthalmology, Epidemiology and Biostatistics, Global Health Sciences, and Francis I Proctor Foundation, University of California San Francisco, San Francisco, CA, United States

*these authors contributed equally

Corresponding Author:

  • Travis C Porco, MPH, PhD
  • Departments of Ophthalmology, Epidemiology and Biostatistics, Global Health Sciences, and Francis I Proctor Foundation
  • University of California San Francisco
  • 490 Illinois St, 2nd Floor
  • San Francisco, CA, 94158
  • United States
  • Phone: 1 415-476-4101
  • Email: travis.porco@ucsf.edu