Context-aware Convolutional Neural Networks for Twitter Sentiment Analysis in Italian

Fiche du document

Date

28 août 2017

Discipline
Périmètre
Langue
Identifiants
Collection

OpenEdition Books

Organisation

OpenEdition

Licences

https://creativecommons.org/licenses/by-nc-nd/4.0/ , info:eu-repo/semantics/openAccess




Citer ce document

Giuseppe Castellucci et al., « Context-aware Convolutional Neural Networks for Twitter Sentiment Analysis in Italian », Accademia University Press, ID : 10.4000/books.aaccademia.2001


Métriques


Partage / Export

Résumé En It

This paper describes the Unitor system that participated to the SENTIment POLarity Classification task proposed in Evalita 2016. The system implements a classification workflow made of several Convolutional Neural Network classifiers, that generalize the linguistic information observed in the training tweets by considering also their context. Moreover, sentiment specific information is injected in the training process by using Polarity Lexicons automatically acquired through the automatic analysis of unlabeled collection of tweets. Unitor achieved the best results in the Subjectivity Classification sub-task, and it scored 2nd in the Polarity Classification sub-task, among about 25 different submissions.

Questo lavoro descrive il sistema Unitor valutato nel task di SENTIment POLarity Classification proposto all’interno di Evalita 2016. Il sistema è basato su un workflow di classificazione implementato usando Convolutional Neural Network, che generalizzano le evidenze osservabili all’interno dei dati di addestramento analizzando i loro contesti e sfruttando lessici specifici per la analisi del sentimento, generati automaticamente. Il sistema ha ottenuto ottimi risultati, ottenendo la miglior performance nel task di Subjectivity Classification e la seconda nel task di Polarity Classification.

document thumbnail

Par les mêmes auteurs

Sur les mêmes sujets

Sur les mêmes disciplines

Exporter en