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.
A kernel-based approach for irony and sarcasm detection in Italian / Santilli, A.; Croce, D.; Basili, R.. - 2263:(2018), pp. 146-151. (Intervento presentato al convegno 6th Evaluation Campaign of Natural Language Processing and Speech Tools for Italian. Final Workshop, EVALITA 2018 tenutosi a Torino; Italia) [10.4000/books.aaccademia.4613].
A kernel-based approach for irony and sarcasm detection in Italian
Santilli A.;
2018
Abstract
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.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
