TWITTIRÒ: a Social Media Corpus with a Multi-layered Annotation for Irony

English. In this paper we describe our work concerning the application of a multi-layered scheme for the fine-grained annotation of irony (Karoui et al., 2017) on a new Italian social media corpus. In applying the annotation on this corpus containing tweets, i.e. TWITTIRÒ, we outlined both strengths and weaknesses of the scheme when applied on Italian, thus giving further clarity on the future directions that can be followed in the multilingual and cross-language perspective. Italiano. In questo articolo descriviamo la creazione di un corpus di testi estratti da social media in italiano e l’applicazione ad esso di uno schema multilivello per l’annotazione a grana fine dell’ironia sviluppato in (Karoui et al., 2017). Nell’applicare l’annotazione a questo corpus composto da messaggi di Twitter, i.e. TWITTIRÒ, abbiamo discusso i punti di forza ed i limiti dello schema stesso, in modo da evidenziare le direzioni da seguire in futuro anche in prospettiva multilingue e cross linguistica.

[1]  Diana Maynard,et al.  Automatic Detection of Political Opinions in Tweets , 2011, #MSM.

[2]  Cristina Bosco,et al.  Annotating Sentiment and Irony in the Online Italian Political Debate on #labuonascuola , 2016, LREC.

[3]  Deirdre Wilson,et al.  On verbal irony , 1992 .

[4]  Diana Maynard,et al.  Who cares about Sarcastic Tweets? Investigating the Impact of Sarcasm on Sentiment Analysis. , 2014, LREC.

[5]  Paolo Rosso,et al.  SemEval-2015 Task 11: Sentiment Analysis of Figurative Language in Twitter , 2015, *SEMEVAL.

[6]  Cristina Bosco,et al.  Developing Corpora for Sentiment Analysis: The Case of Irony and Senti-TUT , 2013, IEEE Intelligent Systems.

[7]  Nathalie Aussenac-Gilles,et al.  Exploring the Impact of Pragmatic Phenomena on Irony Detection in Tweets: A Multilingual Corpus Study , 2017, EACL.

[8]  Richard J. Gerrig,et al.  On the pretense theory of irony. , 1984, Journal of experimental psychology. General.

[9]  Ashley J. Llorens,et al.  Coarse-and Fine-Grained Sentiment Analysis of Social Media Text , 2011 .

[10]  Paolo Rosso,et al.  Figurative messages and affect in Twitter: Differences between #irony, #sarcasm and #not , 2016, Knowl. Based Syst..

[11]  Cristina Bosco,et al.  Analyzing and annotating for sentiment analysis the socio-political debate on #labuonascuola , 2015 .

[12]  Rada Mihalcea,et al.  Characterizing Humour: An Exploration of Features in Humorous Texts , 2009, CICLing.

[13]  Johanna D. Moore,et al.  Twitter Sentiment Analysis: The Good the Bad and the OMG! , 2011, ICWSM.

[14]  D. Sperber,et al.  Irony and the Use-Mention Distinction , 1981 .

[15]  Malvina Nissim,et al.  Overview of the Evalita 2014 SENTIment POLarity Classification Task , 2014 .

[16]  Paolo Rosso,et al.  Finding Humour in the Blogosphere: The Role of WordNet Resources , 2009 .

[17]  Davide Buscaldi,et al.  From humor recognition to irony detection: The figurative language of social media , 2012, Data Knowl. Eng..

[18]  Nathalie Aussenac-Gilles,et al.  Towards a Contextual Pragmatic Model to Detect Irony in Tweets , 2015, ACL.

[19]  Paolo Rosso,et al.  Irony Detection in Twitter , 2016, ACM Trans. Internet Techn..

[20]  H. Grice Reasoning: Further Notes on Logic and Conversation , 2008 .