Cross-domain polarity classification using a knowledge-enhanced meta-classifier

In this paper, we propose the use of meta-learning to combine and enrich those approaches by adding also other knowledge-based features. In addition to the aforementioned classical approaches, our system uses the BabelNet multilingual semantic network to generate features derived from word sense dis...

ver descrição completa

Detalhes bibliográficos
Autores: Franco-Salvador, Marc, Cruz, Fermín L., Troyano Jiménez, José Antonio, Rosso, Paolo
Formato: artículo
Fecha de publicación:2015
País:España
Recursos:Universitat Politècnica de València (UPV)
Repositorio:RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Idioma:inglés
OAI Identifier:oai:riunet.upv.es:10251/63907
Acesso em linha:https://riunet.upv.es/handle/10251/63907
Access Level:acceso abierto
Palavra-chave:Sentiment analysis
Cross-domain polarity classification
Meta-learning
Word sense disambiguation
Semantic network
LENGUAJES Y SISTEMAS INFORMATICOS
Descrição
Resumo:In this paper, we propose the use of meta-learning to combine and enrich those approaches by adding also other knowledge-based features. In addition to the aforementioned classical approaches, our system uses the BabelNet multilingual semantic network to generate features derived from word sense disambiguation and vocabulary expansion. Experimental results show state-of-theart performance on single and cross-domain polarity classification.