5 juin 2019
https://creativecommons.org/licenses/by-nc-nd/4.0/ , info:eu-repo/semantics/openAccess
Lucia Siciliani et al., « The UNIBA System at the EVALITA 2018 Italian Emoji Prediction Task », Accademia University Press, ID : 10.4000/books.aaccademia.4586
This paper describes our participation in the ITAmoji task at EVALITA 2018 (Ronzano et al., 2018). Our approach is based on three sets of features, i.e. micro-blog and keyword features, sentiment lexicon features and semantic features. We exploit these features to train and combine several classifiers using different libraries. The results show how the selected features are not appropriate for training a linear classifier to properly address the emoji prediction task.