Can AI Make Us Laugh? Comparing Jokes Generated by Witscript and a Human Expert

Joe Toplyn, Ori Amir


Abstract
This study compares the funniness of AI-generated jokes and those written by a professional human joke writer, using audience laughter as a direct measure. Prior research has typically relied on numerical ratings, which have limitations. Our findings show that AI-generated jokes elicited as much laughter as human-crafted ones, indicating that advanced AI joke generators can now produce original jokes on par with those of a professional human comedy writer.
Anthology ID:
2025.chum-1.8
Volume:
Proceedings of the 1st Workshop on Computational Humor (CHum)
Month:
January
Year:
2025
Address:
Online
Editors:
Christian F. Hempelmann, Julia Rayz, Tiansi Dong, Tristan Miller
Venues:
chum | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
71–78
Language:
URL:
https://aclanthology.org/2025.chum-1.8/
DOI:
Bibkey:
Cite (ACL):
Joe Toplyn and Ori Amir. 2025. Can AI Make Us Laugh? Comparing Jokes Generated by Witscript and a Human Expert. In Proceedings of the 1st Workshop on Computational Humor (CHum), pages 71–78, Online. Association for Computational Linguistics.
Cite (Informal):
Can AI Make Us Laugh? Comparing Jokes Generated by Witscript and a Human Expert (Toplyn & Amir, chum 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.chum-1.8.pdf