Published on in Vol 4 (2024)

Preprints (earlier versions) of this paper are available at https://preprints.jmir.org/preprint/60678, first published .
Evaluating the Influence of Role-Playing Prompts on ChatGPT’s Misinformation Detection Accuracy: Quantitative Study

Evaluating the Influence of Role-Playing Prompts on ChatGPT’s Misinformation Detection Accuracy: Quantitative Study

Evaluating the Influence of Role-Playing Prompts on ChatGPT’s Misinformation Detection Accuracy: Quantitative Study

Michael Robert Haupt   1, 2, 3 * , PhD ;   Luning Yang   3 * , BS ;   Tina Purnat   4 , MSc ;   Tim Mackey   2, 3, 5 , PhD

1 Department of Cognitive Science, University of California, San Diego, La Jolla, CA, United States

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

3 Global Health Policy & Data Institute, San Diego, CA, United States

4 TH Chan School of Public Health, Harvard University, Boston, MA, United States

5 S-3 Research, San Diego, CA, United States

*these authors contributed equally

Corresponding Author:

  • Tim Mackey, PhD
  • Global Health Program
  • Department of Anthropology
  • University of California, San Diego
  • 9500 Gilman Drive
  • La Jolla, CA, 92093
  • United States
  • Phone: 1 858 534 4145
  • Email: tkmackey@ucsd.edu