SocialIrony

In ironic texts what is literally said is usually negated, and in absence of an explicit negation marker. This makes social computing quite challenging. Detecting irony is very much important for NLP tasks such as polarity classification, sentiment analysis, opinion mining, or reputation analysis. There is a growing interest from the research community in investigating the impact of irony on polarity classification and sentiment analysis. A tasks will be organised at SemEval in 2015 on Sentiment Analysis of Figurative Language in Twitter (http://alt.qcri.org/semeval2015/task11). What are the linguistic patterns that users employ in social media in order to try to be ironic in just maybe 140 characters? Linguistic devices that go beyond positive or negative polarity such as ambiguity, incongruity, unexpectedness and emotional contexts have an important role as triggers of irony. In the talk I will describe how irony is employed in social media texts (Twitter, Amazon, Facebook etc.) and what are the recent state-of-the-art attempts for its automatic detection. At the end of the talk, I will address also the even more challenging and fine-grained problem of distinguishing among irony, sarcasm and satire: e.g. If you find it hard to laugh at yourself, I would be happy to do it for you.