Search Articles

View query in Help articles search

Search Results (1 to 1 of 1 Results)

Download search results: CSV END BibTex RIS


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

In the case of novel events where training data sets do not correspond to emerging circumstances, researchers in infodemiology and related fields should consider hybrid approaches for content coding that incorporate both human annotators and AI techniques (refer to the study by Haupt et al [16] for an example). Human annotators may also be more adept at detecting implicit meanings in text, especially in crises where scientific evidence and circumstances are frequently shifting.

Michael Robert Haupt, Luning Yang, Tina Purnat, Tim Mackey

JMIR Infodemiology 2024;4:e60678