| Full text | |
| Author(s): |
Belisario, Luana Balador
;
Ferreira, Luiz Gabriel
;
Salgueiro Pardo, Thiago Alexandre
;
Quaresma, P
;
Vieira, R
;
Aluisio, S
;
Moniz, H
;
Batista, F
;
Goncalves, T
Total Authors: 9
|
| Document type: | Journal article |
| Source: | COMPUTATIONAL PROCESSING OF THE PORTUGUESE LANGUAGE, PROPOR 2020; v. 12037, p. 9-pg., 2020-01-01. |
| Abstract | |
This paper presents the study and comparison of methods of different paradigms to perform subjectivity classification of sentences in Portuguese. This task is part of the sentiment analysis area and consists of automatically identifying the presence or not of opinative information in texts of interest. We have investigated methods based on sentiment lexicons, graphs, machine learning and word embeddings, using datasets of different domains. We achieve good results, outperforming the previous approaches for Portuguese. (AU) | |
| FAPESP's process: | 18/11479-9 - Subjectivity classification for Portuguese |
| Grantee: | Luiz Gabriel Ferreira |
| Support Opportunities: | Scholarships in Brazil - Scientific Initiation |