Clasificación de polaridad en textos con opiniones en español mediante análisis sintáctico de dependencias

Abstract

This article describes an opinion mining system that classifies the polarity of Spanish texts. We propose a nlp-based approach which performs segmentation, tokenization and pos tagging of texts to then obtain the syntactic structure of sentences by means of a dependency parser. The syntactic structure is then used to address three of the most significant linguistic constructions in the area in question: intensification, adversative subordinate clauses and negation. Experimental results show an improvement in performance with respect to purely lexical approaches and reinforce the idea that parsing is required to achieve a robust and reliable sentiment analysis system.

Extracted Key Phrases

Cite this paper

@article{Vilares2013ClasificacinDP, title={Clasificaci{\'o}n de polaridad en textos con opiniones en espa{\~n}ol mediante an{\'a}lisis sint{\'a}ctico de dependencias}, author={David Vilares and Miguel A. Alonso and Carlos G{\'o}mez-Rodr{\'i}guez}, journal={Procesamiento del Lenguaje Natural}, year={2013}, volume={50}, pages={13-20} }