A Kernel-based Approach for Irony and Sarcasm Detection in Italian

English. This paper describes the UNITOR system that participated to the Irony Detection in Italian Tweets task (IronITA) within the context of EvalIta 2018. The system corresponds to a cascade of Support Vector Machine classifiers. Specific features and kernel functions have been proposed to tackle the different subtasks: Irony Classification and Sarcasm Classification. The proposed system ranked first in the Sarcasm Detection subtask (out of 7 submissions), while it ranked sixth (out of 17 submissions) in the Irony Detection task. Italiano. Questo lavoro descrive il sistema UNITOR che è stato valutato nel corso dell’ Irony Detection in Italian Tweets task IronITA ad EvalIta 2018. Il riconoscimento del sarcasmo e dell’ironia nei tweet corrisponde all’orchestrazione di diversi classificatori di tipo Support Vector Machine (SVM), studiata per risolvere i task legati alla competizione. Rappresentazioni specifiche sono state progettate per modellare i tweet attraverso la applicazione di funzioni kernel diverse utilizzate dai classificatori SVM. Il sistema ha ottenuto risultati promettenti risultando vincitore di 1 dei 2 task proposti.

[1]  T. Landauer,et al.  A Solution to Plato's Problem: The Latent Semantic Analysis Theory of Acquisition, Induction, and Representation of Knowledge. , 1997 .

[2]  Roberto Basili,et al.  Acquiring a Large Scale Polarity Lexicon Through Unsupervised Distributional Methods , 2015, NLDB.

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

[4]  Roberto Basili,et al.  Parsing engineering and empirical robustness , 2002, Natural Language Engineering.

[5]  Roberto Basili,et al.  Context-aware Convolutional Neural Networks for Twitter Sentiment Analysis in Italian , 2016, CLiC-it/EVALITA.

[6]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[7]  Roberto Basili,et al.  A context-based model for Sentiment Analysis in Twitter , 2014, COLING.

[8]  Mário J. Silva,et al.  Clues for detecting irony in user-generated contents: oh...!! it's "so easy" ;-) , 2009, TSA@CIKM.

[9]  Pushpak Bhattacharyya,et al.  Automatic Sarcasm Detection , 2016, ACM Comput. Surv..

[10]  Roberto Basili,et al.  KELP: a Kernel-based Learning Platform , 2018, J. Mach. Learn. Res..

[11]  Nello Cristianini,et al.  Kernel Methods for Pattern Analysis , 2003, ICTAI.

[12]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[13]  Roberto Basili,et al.  A Language Independent Method for Generating Large Scale Polarity Lexicons , 2016, LREC.

[14]  Paolo Rosso,et al.  Overview of the EVALITA 2018 Task on Irony Detection in Italian Tweets (IronITA) , 2018, EVALITA@CLiC-it.