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

Current approaches to single and cross-domain polarity classification usually use bag of words, n-grams or lexical resource-based classifiers. 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 a...

Descripción completa

Detalles Bibliográficos
Autores: Franco Salvador, Marc, Cruz Mata, Fermín, Troyano Jiménez, José Antonio, Rosso, Paolo
Tipo de recurso: artículo
Estado:Versión enviada para evaluación y publicación
Fecha de publicación:2015
País:España
Institución:Universidad de Sevilla (US)
Repositorio:idUS. Depósito de Investigación de la Universidad de Sevilla
OAI Identifier:oai:idus.us.es:11441/99638
Acceso en línea:https://hdl.handle.net/11441/99638
https://doi.org/10.1016/j.knosys.2015.05.020
Access Level:acceso abierto
Palabra clave:Sentiment analysis
Cross-domain polarity classification
Meta-learning
Word sense disambiguation
Semantic network
Descripción
Sumario:Current approaches to single and cross-domain polarity classification usually use bag of words, n-grams or lexical resource-based classifiers. 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-the-art performance on single and cross-domain polarity classification. Contrary to other approaches, ours is generic. These results were obtained without any domain adaptation technique. Moreover, the use of meta-learning allows our approach to obtain the most stable results across domains. Finally, our empirical analysis provides interesting insights on the use of semantic network-based features.