Procesamiento de Lenguaje Natural para el Análisis de Lenguaje Subjetivo

we describe the application of natural language processing (nlp) technology to the analysis of subjective language. in particular we concentrate on the problem of opinion classification of textual material extracted from business-related data-sources. we study the derivation of sentiment values for words from the sentiwordnet lexical resource and use them for text interpretation to produce word, sentence, and textbased sentiment features for opinion classification. we use word-based and sentimentbased features to induce a classifier based on the use of support vector machines achieving state of the art results. we also show preliminary experiments where the use of summaries before opinion classification provides competitive advantage over the use of full documents when the documents are long and contain both subjective and non-subjective material.