Clues for detecting irony in user-generated contents: oh...!! it's "so easy" ;-)

By Paula Carvalho, L. Sarmento, Mário J. Silva, Eugénio de Oliveira. TSA@CIKM, 2009

324 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Experimental and Cognitive Psychology

View Paper: https://www.semanticscholar.org/paper/ce3fd4dbfb7ae6db44e2450f5213c140c689d2d9

How researchers see this paper

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

In Artificial Intelligence

In Experimental and Cognitive Psychology

Citations in the corpus

Humans Require Context to Infer Ironic Intent (so Computers Probably do, too) (2014, background): “More specifically, annotators have provided binary ‘labels’ for each sentence indicating whether or not they (the annotator) believe it was intended by the author ironically (or not).”
Sentiment Knowledge Discovery in Twitter Streaming Data (2010, background): “Also, some tweets may contain sarcasm or irony [4] as in the following example:”
Challenges in Sentiment Analysis (2017, unknown): “There is growing interest in detecting ﬁgurative language, especially irony and sarcasm (Carvalho, Sarmento, Silva, & De Oliveira, 2009; Reyes, Rosso, & Veale, 2013; Veale & Hao, 2010; Filatova, 2012; Gonz´alez-Ib´anez, Muresan, & Wacholder, 2011).”
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”
Modelling input texts: from Tree Kernels to Deep Learning (2015, background): “objective parts of a document [107, 187], opinion holders [70] or more complex sentiments and emotions [22], in particular, as irony or sarcasm [26, 123].”
Sentiment Analysis: An Overview from Linguistics (2016, unknown): “Some attempts have been made at using emoticons, where the emoticon carries what could be interpreted as the opposite polarity of the preceding statements (Carvalho et al 2009, Tsur et al 2010).”
Classifying sentiment in microblogs: is brevity an advantage? (2010, background): “Car-valho et al. found that non-standard surface features such as a heavy punctuation and emoticons are key to detecting irony in user-generated content [3].”
Towards Multimodal Sarcasm Detection (An _Obviously_ Perfect Paper) (2019, background): “…Traditional approaches for detecting sarcasm in text have considered rule-based techniques (Veale and Hao, 2010), lexical and pragmatic features (Carvalho et al., 2009), stylistic features (Davidov et al., 2010), situational disparity (Riloff et al., 2013), incongruity (Joshi et al., 2015), or…”
Identifying Sarcasm in Twitter: A Closer Look (2011, background): “…show that non-linguistic cues such as emoticons are helpful in interpreting non-literal meaning such as sarcasm and irony in user generated content (Derks et al., 2008; Carvalho et al., 2009), we explored how much emoticons help humans to distinguish sarcas-tic from positive and negative tweets.”
Harnessing Context Incongruity for Sarcasm Detection (2015, methodology): “Carvalho et al. (2009) use simple linguistic features like interjection, changed names, etc. for irony detection.”
Sarcasm as Contrast between a Positive Sentiment and Negative Situation (2013, background): “In opinionated user posts, Carvalho et al. (2009) found oral or gestural expressions, represented using punctuation and other keyboard characters, to be more predictive of irony1 in contrast to features representing structured linguistic knowledge in Por- 1They adopted the term ‘irony’ instead of…”
A Deeper Look into Sarcastic Tweets Using Deep Convolutional Neural Networks (2016, background): “…Carvalho et al., 2009; Barbieri et al., 2014), unsupervised pattern mining approach (Maynard and Greenwood, 2014), semi-supervised approach (Riloff et al., 2013) and n-grams based approach (Tsur et al., 2010; Davidov et al., 2010; Pt´acek et al., 2014; Joshi et al., 2015) with sentiment features.”