A text mining-based approach for analyzing information retrieval in Spanish: Music data collection as a case study

Abstract

This paper presents a text mining-based search approach aimed at information retrieval in the Spanish language. For this purpose, a tool has been developed in order to facilitate and automate the analysis and retrieval, allowing the user to apply different analyzers when carrying out a query, to index and delete documents stored in the system and to evaluate the recovery process. To this extent, a dataset consisting in 27 songs has been used as a case study. Different queries have been made to investigate about the best fitting approaches to the Spanish language and their suitability depending on the query text.