3 septembre 2021
https://www.openedition.org/12554 , info:eu-repo/semantics/openAccess
Luca Bacco et al., « A Machine Learning approach for Sentiment Analysis for Italian Reviews in Healthcare », Accademia University Press, ID : 10.4000/books.aaccademia.8225
In this paper, we present our approach to the task of binary sentiment classification for Italian reviews in healthcare domain. We first collected a new dataset for such domain. Then, we compared the results obtained by two different systems, one including a Support Vector Machine and one with BERT. For the first one, we linguistic pre–processed the dataset to extract hand-crafted features exploited by the classifier. For the second one, we over-sampled the dataset to achieve better results. Our results show that the SVM-based system, without the worry of having to oversample, has better performance than the BERT-based one, achieving an F1-score of 91.21%.