Automatic Sarcasm Detection

Abstract

Automatic sarcasm detection is the task of predicting sarcasm in text. This is a crucial step to sentiment analysis, considering prevalence and challenges of sarcasm in sentiment-bearing text. Beginning with an approach that used speech-based features, sarcasm detection has witnessed great interest from the sentiment analysis community. This paper is the first known compilation of past work in automatic sarcasm detection. We observe three milestones in the research so far: semi-supervised pattern extraction to identify implicit sentiment, use of hashtag-based supervision, and use of context beyond target text. In this paper, we describe datasets, approaches, trends and issues in sarcasm detection. We also discuss representative performance values, shared tasks and pointers to future work, as given in prior works. In terms of resources that could be useful for understanding state-of-the-art, the survey presents several useful illustrations -most prominently, a table that summarizes past papers along different dimensions such as features,

Exploring the fine-grained analysis and automatic detection of irony on Twitter

“…As observed in our corpus and stated by Joshi et al (2017), irony is often realised by means of a polarity contrast, with one of the polarities often being implicit. Such implicit polarity expressions would enable us to recognise polarity contrasts in tweets like example 14, which cannot be captured using sentiment lexicons.…”

“…We made use of a support vector machine as implemented in the LIBSVM library (Chang and Lin 2011), since the algorithm has been successfully combined with large feature sets and its good performance for similar tasks has been recognised (Joshi et al 2017).…”

“…We discuss the most relevant studies for the present research, but refer to the papers by Wallace (2015) and Joshi et al (2017) for a more detailed overview. Important to note is that when discussing related research, we refer to irony using the terminology employed by the corresponding researchers [i.e.…”

“…As described by Joshi et al (2017), computational approaches to irony can be roughly classified into rule-based and (supervised and unsupervised) machine learning-based. While rule-based approaches mostly rely upon lexicon and word-based information, machine learning often exploits rich feature sets that are either manually defined or learned in neural networks.…”

SemEval-2018 Task 3: Irony Detection in English Tweets

“…As described by Joshi et al (2017), recent approaches to irony can roughly be classified as either rule-based or (supervised and unsupervised) machine learning-based. While rule-based approaches mostly rely upon lexical information and require no training, machine learning invariably makes use of training data and exploits different types of information sources (or features), such as bags of words, syntactic patterns, sentiment information or semantic relatedness.…”