Proceedings of the Eighth ACM International Conference on Web Search and Data Mining 2015
DOI: 10.1145/2684822.2685316
|View full text |Cite
|
Sign up to set email alerts
|

Sarcasm Detection on Twitter

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 difficult 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 the… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

1
44
0

Year Published

2017
2017
2020
2020

Publication Types

Select...
5
3
1

Relationship

0
9

Authors

Journals

citations
Cited by 280 publications
(45 citation statements)
references
References 32 publications
1
44
0
Order By: Relevance
“…There are four groups of classifications, namely the style of comparison, contradiction, linkage, and repetition. In accordance with this discussion, the style of language that is associated with rude speech and impoliteness is the style of sarcasm [3], [7].…”
Section: Introductionsupporting
confidence: 55%
“…There are four groups of classifications, namely the style of comparison, contradiction, linkage, and repetition. In accordance with this discussion, the style of language that is associated with rude speech and impoliteness is the style of sarcasm [3], [7].…”
Section: Introductionsupporting
confidence: 55%
“…Perhaps most notably, it signals that addiction to nicotine through hookah is not seen as a health risk that is problematic or would dissuade potential customers. In an Internet culture that often embraces irony and sarcasm (Rajadesingan, Zafarani, & Liu, 2015; Reyes, Rosso, & Veale, 2013), #HookahAddiction is not a warning statement so much as a joke or a badge of honor. Further research on the portrayal of nicotine addiction in social media would be valuable to inform the public health response to evolving perceptions of addiction.…”
Section: Discussionmentioning
confidence: 99%
“…In the human‐computer interaction (HCI) context, humor has been shown to enhance the user experience, engagement, and personification (Khooshabeh et al, 2011; Niculescu et al, 2013). The HCI literature related to humor usually clusters around studies focused on developing and testing algorithms for generating humor, such as puns (Valitutti et al, 2013; Stock and Strapparava; 2015; Taylor and Raskin, 2013; Ritschel et al, 2019), or detecting humor, irony and sarcasm (Kiddon and Brun; 2011; Rajadesingan et al, 2015; Zhang and Liu, 2014; Mihalcea and Strapparava, 2006; Yang et al, 2015; Miller et al, 2017).…”
Section: Literature Reviewmentioning
confidence: 99%