Analysis of Aspect Extraction Methods in Regular Opinions

This work presents a comparative analysis between the main approaches used at the task of Extraction of Aspects in reports about products and services on web sites. Adaptations of four methods of extraction of aspects were implemented and evaluated using two distinct Corpora, one in Portuguese and a...

Descripción completa

Detalles Bibliográficos
Autores: Vieira, João Paulo Albuquerque, Moura, Raimundo Santos
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2020
País:Brasil
Institución:Sociedade Brasileira de Computação (SBC)
Repositorio:Brazilian Journal of Information Systems
Idioma:portugués
OAI Identifier:oai:journals-sol.sbc.org.br:article/796
Acceso en línea:https://journals-sol.sbc.org.br/index.php/isys/article/view/796
Access Level:acceso abierto
Palabra clave:Opinion Mining
Sentiment Analysis
Aspect Extraction
Mineração de Opinião
Análise de Sentimentos
Extração de Aspectos
Descripción
Sumario:This work presents a comparative analysis between the main approaches used at the task of Extraction of Aspects in reports about products and services on web sites. Adaptations of four methods of extraction of aspects were implemented and evaluated using two distinct Corpora, one in Portuguese and another in English. On the experiments performed it was observed that the approach using supervised learning (convolutional neural networks) obtained better results on the others.