petersuber on Nostr: New study: Researchers used #ChatGPT to judge the "politeness" and "sentiment" of ...

New study: Researchers used #ChatGPT to judge the "politeness" and "sentiment" of #PeerReview reports in high-impact medical journals. They found no significant differences based on author #gender but significant differences based on author nationality. "Papers from the #MiddleEast, #LatinAmerica, or #Africa exhibited lower sentiment and politeness scores compared to those from North America, Europe, or Pacific and Asia."
https://www.jmir.org/2024/1/e57667