Inside jokes: Identifying humorous cartoon captions

Dafna Shahaf; Eric Horvitz; Robert Mankoff

doi:10.1145/2783258.2783388

Inside jokes: Identifying humorous cartoon captions

Dafna Shahaf, Eric Horvitz, Robert Mankoff

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

50 Scopus citations

Abstract

Humor is an integral aspect of the human experience. Motivated by the prospect of creating computational models of humor, we study the influence of the language of cartoon captions on the perceived humorousness of the cartoons. Our studies are based on a large corpus of crowdsourced cartoon captions that were submitted to a contest hosted by the New Yorker. Having access to thousands of captions submitted for the same image allows us to analyze the breadth of responses of people to the same visual stimulus. We first describe how we acquire judgments about the humorousness of different captions. Then, we detail the construction of a corpus where captions deemed funnier are paired with less-funny captions for the same cartoon. We analyze the caption pairs and find significant differences between the funnier and less-funny captions. Next, we build a classifier to identify funnier captions automatically. Given two captions and a cartoon, our classifier picks the funnier one 69% of the time for captions hinging on the same joke, and 64% of the time for any pair of captions. Finally, we use the classifier to find the best captions and study how its predictions could be used to significantly reduce the load on the cartoon contest's judges.

Original language	English
Title of host publication	KDD 2015 - Proceedings of the 21st ACM SIGKDD Conference on Knowledge Discovery and Data Mining
Publisher	Association for Computing Machinery
Pages	1065-1074
Number of pages	10
ISBN (Electronic)	9781450336642
DOIs	https://doi.org/10.1145/2783258.2783388
State	Published - 10 Aug 2015
Externally published	Yes
Event	21st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2015 - Sydney, Australia Duration: 10 Aug 2015 → 13 Aug 2015

Publication series

Name	Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
Volume	2015-August

Conference

Conference	21st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2015
Country/Territory	Australia
City	Sydney
Period	10/08/15 → 13/08/15

Bibliographical note

Publisher Copyright:
© 2015 ACM.

Keywords

Cartoon
Cartoon caption
Humor

Access to Document

10.1145/2783258.2783388

Cite this

Shahaf, D., Horvitz, E., & Mankoff, R. (2015). Inside jokes: Identifying humorous cartoon captions. In KDD 2015 - Proceedings of the 21st ACM SIGKDD Conference on Knowledge Discovery and Data Mining (pp. 1065-1074). (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; Vol. 2015-August). Association for Computing Machinery. https://doi.org/10.1145/2783258.2783388

@inproceedings{1211f589ce594028bceaac665bc4d4d7,

title = "Inside jokes: Identifying humorous cartoon captions",

abstract = "Humor is an integral aspect of the human experience. Motivated by the prospect of creating computational models of humor, we study the influence of the language of cartoon captions on the perceived humorousness of the cartoons. Our studies are based on a large corpus of crowdsourced cartoon captions that were submitted to a contest hosted by the New Yorker. Having access to thousands of captions submitted for the same image allows us to analyze the breadth of responses of people to the same visual stimulus. We first describe how we acquire judgments about the humorousness of different captions. Then, we detail the construction of a corpus where captions deemed funnier are paired with less-funny captions for the same cartoon. We analyze the caption pairs and find significant differences between the funnier and less-funny captions. Next, we build a classifier to identify funnier captions automatically. Given two captions and a cartoon, our classifier picks the funnier one 69% of the time for captions hinging on the same joke, and 64% of the time for any pair of captions. Finally, we use the classifier to find the best captions and study how its predictions could be used to significantly reduce the load on the cartoon contest's judges.",

keywords = "Cartoon, Cartoon caption, Humor",

author = "Dafna Shahaf and Eric Horvitz and Robert Mankoff",

note = "Publisher Copyright: {\textcopyright} 2015 ACM.; 21st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2015 ; Conference date: 10-08-2015 Through 13-08-2015",

year = "2015",

month = aug,

day = "10",

doi = "10.1145/2783258.2783388",

language = "אנגלית",

series = "Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining",

publisher = "Association for Computing Machinery",

pages = "1065--1074",

booktitle = "KDD 2015 - Proceedings of the 21st ACM SIGKDD Conference on Knowledge Discovery and Data Mining",

}

Shahaf, D, Horvitz, E & Mankoff, R 2015, Inside jokes: Identifying humorous cartoon captions. in KDD 2015 - Proceedings of the 21st ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, vol. 2015-August, Association for Computing Machinery, pp. 1065-1074, 21st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2015, Sydney, Australia, 10/08/15. https://doi.org/10.1145/2783258.2783388

Inside jokes: Identifying humorous cartoon captions. / Shahaf, Dafna; Horvitz, Eric; Mankoff, Robert.
KDD 2015 - Proceedings of the 21st ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery, 2015. p. 1065-1074 (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; Vol. 2015-August).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Inside jokes

T2 - 21st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2015

AU - Shahaf, Dafna

AU - Horvitz, Eric

AU - Mankoff, Robert

PY - 2015/8/10

Y1 - 2015/8/10

N2 - Humor is an integral aspect of the human experience. Motivated by the prospect of creating computational models of humor, we study the influence of the language of cartoon captions on the perceived humorousness of the cartoons. Our studies are based on a large corpus of crowdsourced cartoon captions that were submitted to a contest hosted by the New Yorker. Having access to thousands of captions submitted for the same image allows us to analyze the breadth of responses of people to the same visual stimulus. We first describe how we acquire judgments about the humorousness of different captions. Then, we detail the construction of a corpus where captions deemed funnier are paired with less-funny captions for the same cartoon. We analyze the caption pairs and find significant differences between the funnier and less-funny captions. Next, we build a classifier to identify funnier captions automatically. Given two captions and a cartoon, our classifier picks the funnier one 69% of the time for captions hinging on the same joke, and 64% of the time for any pair of captions. Finally, we use the classifier to find the best captions and study how its predictions could be used to significantly reduce the load on the cartoon contest's judges.

AB - Humor is an integral aspect of the human experience. Motivated by the prospect of creating computational models of humor, we study the influence of the language of cartoon captions on the perceived humorousness of the cartoons. Our studies are based on a large corpus of crowdsourced cartoon captions that were submitted to a contest hosted by the New Yorker. Having access to thousands of captions submitted for the same image allows us to analyze the breadth of responses of people to the same visual stimulus. We first describe how we acquire judgments about the humorousness of different captions. Then, we detail the construction of a corpus where captions deemed funnier are paired with less-funny captions for the same cartoon. We analyze the caption pairs and find significant differences between the funnier and less-funny captions. Next, we build a classifier to identify funnier captions automatically. Given two captions and a cartoon, our classifier picks the funnier one 69% of the time for captions hinging on the same joke, and 64% of the time for any pair of captions. Finally, we use the classifier to find the best captions and study how its predictions could be used to significantly reduce the load on the cartoon contest's judges.

KW - Cartoon

KW - Cartoon caption

KW - Humor

UR - http://www.scopus.com/inward/record.url?scp=84954106965&partnerID=8YFLogxK

U2 - 10.1145/2783258.2783388

DO - 10.1145/2783258.2783388

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:84954106965

T3 - Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

SP - 1065

EP - 1074

BT - KDD 2015 - Proceedings of the 21st ACM SIGKDD Conference on Knowledge Discovery and Data Mining

PB - Association for Computing Machinery

Y2 - 10 August 2015 through 13 August 2015

ER -

Inside jokes: Identifying humorous cartoon captions

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this