Cards Against AI: Predicting Humor in a Fill-in-the-blank Party Game

Dan Ofer, Dafna Shahaf


Abstract
Humor is an inherently social phenomenon, with humorous utterances shaped by what is socially and culturally accepted. Understanding humor is an important NLP challenge, with many applications to human-computer interactions. In this work we explore humor in the context of Cards Against Humanity – a party game where players complete fill-in-the-blank statements using cards that can be offensive or politically incorrect.We introduce a novel dataset of 300,000 online games of Cards Against Humanity, including 785K unique jokes, analyze it and provide insights. We trained machine learning models to predict the winning joke per game, achieving performance twice as good (20%) as random, even without any user information.On the more difficult task of judging novel cards, we see the models’ ability to generalize is moderate. Interestingly, we find that our models are primarily focused on punchline card, with the context having little impact.Analyzing feature importance, we observe that short, crude, juvenile punchlines tend to win.
Anthology ID:
2022.findings-emnlp.394
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5397–5403
Language:
URL:
https://aclanthology.org/2022.findings-emnlp.394
DOI:
10.18653/v1/2022.findings-emnlp.394
Bibkey:
Cite (ACL):
Dan Ofer and Dafna Shahaf. 2022. Cards Against AI: Predicting Humor in a Fill-in-the-blank Party Game. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 5397–5403, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Cards Against AI: Predicting Humor in a Fill-in-the-blank Party Game (Ofer & Shahaf, Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-emnlp.394.pdf
Note:
 2022.findings-emnlp.394.note.pdf
Software:
 2022.findings-emnlp.394.software.zip
Video:
 https://aclanthology.org/2022.findings-emnlp.394.mp4