An Exploratory Study of the Use of Senses, Syntax and Cross-Linguistic Information for Subjectivity Detection in Spanish

Abstract

This work presents an exploratory study of Subjectivity Detection for Spanish This study aims to evaluate the use of dependency relations, word senses and cross-linguistic information in Subjectivity Detection task. The first steps of this method include the labeling process of a Spanish corpus and a Word Sense Disambiguation algorithm. Then cross-linguistic English-Spanish information is obtained from Semcorcorpus and used together with the Spanish data. Finally, this approach (using all gathered information and supervised algorithms) was tested showing better results than the baseline method in general.