Identifying Sarcasm in Twitter: A Closer Look

By Roberto I. González-Ibáñez, Smaranda Muresan, Nina Wacholder. Annual Meeting of the Association for Computational Linguistics, 2011

699 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/55e36d6b45c91a0daa49234bd47b856470d6825c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

A survey of sentiment analysis in social media (2018, background): “[41] tried to solve the problem of automatically detecting sarcasm in Tweets.”
Using Hashtags to Capture Fine Emotion Categories from Tweets (2015, background): “Like Gonz´alez-Ib´a˜nez et al. (2011), we removed tweets that did not have the hashtag of interest at the end of the message.”
CARER: Contextualized Affect Representations for Emotion Recognition (2018, methodology): “We bootstrap a set of noisy labels to obtain large-scale emotion tweets, and then perform annotation via distant supervision as in (Go et al., 2009; González-Ibánez et al., 2011; Wang et al., 2012; Mohammad and Kiritchenko, 2015; Abdul-Mageed and Ungar, 2017).”
Fracking Sarcasm using Neural Network (2016, background): “(González-Ibánez et al., 2011) views sarcasm as a conformation of lexical and pragmatic factors such as emoticons and profile references in social media.”
A Deeper Look into Sarcastic Tweets Using Deep Convolutional Neural Networks (2016, methodology): “(Gonz´alez-Ib´anez et al., 2011) used support vector machine (SVM) and logistic regression over a feature set of unigrams, dictionary-based lexical features and pragmatic features (e.g., emoticons) and compared the performance of the classiﬁer with that of humans.”
Harnessing Context Incongruity for Sarcasm Detection (2015, methodology): “Gonzalez-Ibanez et al. (2011) study the role of unigrams and emoticons in sarcasm detection.”
#Emotional Tweets (2012, background): “First Joint Conference on Lexical and Computational Semantics (*SEM), pages 246–255, Montréal, Canada, June 7-8, 2012. c©2012 Association for Computational Linguistics”
SemEval-2018 Task 3: Irony Detection in English Tweets (2018, background): “…include punctuation mark/interjection counts (e.g Davi-dov et al., 2010), sentiment lexicon scores (e.g. Bouazizi and Ohtsuki, 2016; Far´ıas et al., 2016), emoji (e.g. Gonz´alez-Ib´a˜nez et al., 2011), writing style, emotional scenarios, part of speech-patterns (e.g. Reyes et al., 2013), and so on.”
Humans Require Context to Infer Ironic Intent (so Computers Probably do, too) (2014, background): “…been a flurry of interesting work on automatic irony detection (Tepperman et al., 2006; Davidov et al., 2010; Carvalho et al., 2009; Burfoot and Baldwin, 2009; Tsur et al., 2010; González-Ibáñez et al., 2011; Filatova, 2012; Reyes et al., 2012; Lukin and Walker, 2013; Riloff et al., 2013).”
From humor recognition to irony detection: The figurative language of social media (2012, background): “For instance, the research works concerning automatic humor generation [6,41] and automatic humor recognition [29,28,36], as well as the ones concerning irony detection [44,45,10,35], satire detection [9], and sarcasm detection [43,18], have shown the feasibility of computationally dealing with figu”
Emotional States vs. Emotional Words in Social Media (2015, background): “Should we assume this person is in a negative state of mind? If these issues are not enough, it’s extremely difficult for even the most sophisticated NLP techniques or human raters to detect sarcasm or irony [12].”
SemEval-2015 Task 10: Sentiment Analysis in Twitter (2015, background): “, 2003), and even for sarcasm identification (González-Ibáñez et al., 2011; Liebrecht et al., 2013).”
Sentiment Analysis and Opinion Mining (2012, methodology): “The work of González-Ibáñez et al. (2011) studied the problem in the context of sentiment analysis using Twitter data, i.e., to distinguish sarcastic tweets and non-sarcastic tweets that directly convey positive or negative opinions (neutral utterances were not considered).”