A multidimensional approach for detecting irony in Twitter (Information…
A multidimensional approach for detecting irony in Twitter
Irony in language, theoratical problem
Sarcasm and irony
In this current work, we aim to analyze irony in terms of a multidimensional model of textual elements. We thus identify a set of discriminative features to automatically differentiate an ironic text from a non-ironic one.
The impact of this work thus lies in the way it deals with non-factual information that is linguistically expressed, such as sentiment, attitude, humor and mood. These are inherent to our social activities, and are therefore extremely useful in the automatic mining of new knowledge.
Rather, we must try to identify specific aspects and forms of irony that are susceptible to computational analysis, and from these individual treatments attempt to synthesize a gradually broader solution.
Opinion mining (cf. Sarmento et al. 2009), where the authors note the role of irony in discriminating negative from positive opinions), and advertising (cf. Kreuz 2001, about the function of irony to increase message effectiveness in advertising), among others.
(cf. Reyes et al. 2009 about the importance of determining the presence of irony in order to assign fine-grained polarity levels),
Problem of irony cuts through every aspect of language, from pronunciation to lexical choice, syntactic structure, semantics and conceptualization. As such, it is unrealistic to seek a computational silver bullet for irony, and a general solution will not be found in any single technique or algorithm.
Irony. This linguistic phenomenon, which is widespread in web content, has important implications for tasks such as sentiment analysis
We describe here a set of textual features for recognizing irony at a linguistic level, especially in short texts created via social media such as Twitter postings or ‘‘tweets’’.
Our experiments concern four freely available data sets that were retrieved from Twitter using content words (e.g. ‘‘Toyota’’) and user-generated tags (e.g. ‘‘#irony’’).
We construct a new model of irony detection that is assessed along two dimensions: representativeness and relevance