Bernhard Clemm
@BernhardClemm
computational social scientist @gesis_org | data editor @polcommjournal
ID:2849734774
http://bernhardclemm.com 29-10-2014 12:24:15
687 Tweets
703 Followers
761 Following
This paper tests the performance of GPT4 in text coding across a range of common political science coding tasks in 4 languages. Michael Heseltine & Bernhard Clemm find that GPT4 coding is highly accurate, especially for shorter texts. Read more here: doi.org/10.1177/205316…