Sarcasm detection on twitter:A behavioral modeling approach

Ashwin Rajadesingan; Reza Zafarani; Huan Liu

doi:10.1145/2684822.2685316

Sarcasm detection on twitter:A behavioral modeling approach

Ashwin Rajadesingan, Reza Zafarani, Huan Liu

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

284 Scopus citations

Abstract

Sarcasm is a nuanced form of language in which individuals state the opposite of what is implied. With this intentional ambiguity, sarcasm detection has always been a challenging task, even for humans. Current approaches to automatic sarcasm detection rely primarily on lexical and linguistic cues. This paper aims to address the di-cult task of sarcasm detection on Twitter by leveraging behavioral traits intrinsic to users expressing sarcasm. We identify such traits using the user's past tweets. We employ theories from behavioral and psychological studies to construct a behavioral modeling framework tuned for detecting sarcasm. We evaluate our framework and demonstrate its efficiency in identifying sarcastic tweets.

Original language	English (US)
Title of host publication	WSDM 2015 - Proceedings of the 8th ACM International Conference on Web Search and Data Mining
Publisher	Association for Computing Machinery
Pages	97-106
Number of pages	10
ISBN (Electronic)	9781450333177
DOIs	https://doi.org/10.1145/2684822.2685316
State	Published - Feb 2 2015
Event	8th ACM International Conference on Web Search and Data Mining, WSDM 2015 - Shanghai, China Duration: Jan 31 2015 → Feb 6 2015

Publication series

Name	WSDM 2015 - Proceedings of the 8th ACM International Conference on Web Search and Data Mining

Other

Other	8th ACM International Conference on Web Search and Data Mining, WSDM 2015
Country/Territory	China
City	Shanghai
Period	1/31/15 → 2/6/15

Keywords

Behavioral modeling
Sarcasm detection
Social media

ASJC Scopus subject areas

Computer Networks and Communications

Access to Document

10.1145/2684822.2685316

Cite this

Rajadesingan, A., Zafarani, R., & Liu, H. (2015). Sarcasm detection on twitter:A behavioral modeling approach. In WSDM 2015 - Proceedings of the 8th ACM International Conference on Web Search and Data Mining (pp. 97-106). (WSDM 2015 - Proceedings of the 8th ACM International Conference on Web Search and Data Mining). Association for Computing Machinery. https://doi.org/10.1145/2684822.2685316

Sarcasm detection on twitter:A behavioral modeling approach. / Rajadesingan, Ashwin; Zafarani, Reza; Liu, Huan.
WSDM 2015 - Proceedings of the 8th ACM International Conference on Web Search and Data Mining. Association for Computing Machinery, 2015. p. 97-106 (WSDM 2015 - Proceedings of the 8th ACM International Conference on Web Search and Data Mining).

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

Rajadesingan, A, Zafarani, R & Liu, H 2015, Sarcasm detection on twitter:A behavioral modeling approach. in WSDM 2015 - Proceedings of the 8th ACM International Conference on Web Search and Data Mining. WSDM 2015 - Proceedings of the 8th ACM International Conference on Web Search and Data Mining, Association for Computing Machinery, pp. 97-106, 8th ACM International Conference on Web Search and Data Mining, WSDM 2015, Shanghai, China, 1/31/15. https://doi.org/10.1145/2684822.2685316

Rajadesingan A, Zafarani R, Liu H. Sarcasm detection on twitter:A behavioral modeling approach. In WSDM 2015 - Proceedings of the 8th ACM International Conference on Web Search and Data Mining. Association for Computing Machinery. 2015. p. 97-106. (WSDM 2015 - Proceedings of the 8th ACM International Conference on Web Search and Data Mining). doi: 10.1145/2684822.2685316

@inproceedings{806077291e8a4d85a425f5d8eda9993e,

title = "Sarcasm detection on twitter:A behavioral modeling approach",

abstract = "Sarcasm is a nuanced form of language in which individuals state the opposite of what is implied. With this intentional ambiguity, sarcasm detection has always been a challenging task, even for humans. Current approaches to automatic sarcasm detection rely primarily on lexical and linguistic cues. This paper aims to address the di-cult task of sarcasm detection on Twitter by leveraging behavioral traits intrinsic to users expressing sarcasm. We identify such traits using the user's past tweets. We employ theories from behavioral and psychological studies to construct a behavioral modeling framework tuned for detecting sarcasm. We evaluate our framework and demonstrate its efficiency in identifying sarcastic tweets.",

keywords = "Behavioral modeling, Sarcasm detection, Social media",

author = "Ashwin Rajadesingan and Reza Zafarani and Huan Liu",

note = "Publisher Copyright: Copyright {\textcopyright} 2015 ACM.; 8th ACM International Conference on Web Search and Data Mining, WSDM 2015 ; Conference date: 31-01-2015 Through 06-02-2015",

year = "2015",

month = feb,

day = "2",

doi = "10.1145/2684822.2685316",

language = "English (US)",

series = "WSDM 2015 - Proceedings of the 8th ACM International Conference on Web Search and Data Mining",

publisher = "Association for Computing Machinery",

pages = "97--106",

booktitle = "WSDM 2015 - Proceedings of the 8th ACM International Conference on Web Search and Data Mining",

}

TY - GEN

T1 - Sarcasm detection on twitter:A behavioral modeling approach

AU - Rajadesingan, Ashwin

AU - Zafarani, Reza

AU - Liu, Huan

PY - 2015/2/2

Y1 - 2015/2/2

N2 - Sarcasm is a nuanced form of language in which individuals state the opposite of what is implied. With this intentional ambiguity, sarcasm detection has always been a challenging task, even for humans. Current approaches to automatic sarcasm detection rely primarily on lexical and linguistic cues. This paper aims to address the di-cult task of sarcasm detection on Twitter by leveraging behavioral traits intrinsic to users expressing sarcasm. We identify such traits using the user's past tweets. We employ theories from behavioral and psychological studies to construct a behavioral modeling framework tuned for detecting sarcasm. We evaluate our framework and demonstrate its efficiency in identifying sarcastic tweets.

AB - Sarcasm is a nuanced form of language in which individuals state the opposite of what is implied. With this intentional ambiguity, sarcasm detection has always been a challenging task, even for humans. Current approaches to automatic sarcasm detection rely primarily on lexical and linguistic cues. This paper aims to address the di-cult task of sarcasm detection on Twitter by leveraging behavioral traits intrinsic to users expressing sarcasm. We identify such traits using the user's past tweets. We employ theories from behavioral and psychological studies to construct a behavioral modeling framework tuned for detecting sarcasm. We evaluate our framework and demonstrate its efficiency in identifying sarcastic tweets.

KW - Behavioral modeling

KW - Sarcasm detection

KW - Social media

UR - http://www.scopus.com/inward/record.url?scp=84928731665&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84928731665&partnerID=8YFLogxK

U2 - 10.1145/2684822.2685316

DO - 10.1145/2684822.2685316

M3 - Conference contribution

AN - SCOPUS:84928731665

T3 - WSDM 2015 - Proceedings of the 8th ACM International Conference on Web Search and Data Mining

SP - 97

EP - 106

BT - WSDM 2015 - Proceedings of the 8th ACM International Conference on Web Search and Data Mining

PB - Association for Computing Machinery

T2 - 8th ACM International Conference on Web Search and Data Mining, WSDM 2015

Y2 - 31 January 2015 through 6 February 2015

ER -

Sarcasm detection on twitter:A behavioral modeling approach

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this