Análise e avaliação experimentais de técnicas para recuperação de documentos jurisprudenciais

Abstract

Stemming algorithms are commonly used during textual Preprocessing phase in order to reduce data dimensionality. However, this reduction presents different efficacy levels depending on the Domain that it’s applied to. Thus, for instance, there are reports in the literature that show the effect of radicalization when applied to dictionaries or textual bases of news. On the other hand, we have not found any studies analyzing the impact of radicalization on Brazilian judicial jurisprudence, composed of decisions handed down by the judiciary, a fundamental instrument for legal professionals to play their role. Thus, this work presents the results obtained through the analysis and experimental evaluation of the stemmers applied on real jurisprudential documents, originating from the Court of Justice of the State of Sergipe. The results showed that, among the analyzed algorithms, the RSLP possessed the greatest capacity of dimensionality reduction of the data. The RSLP-S and UniNE algorithms, the less aggressive stemmers, presented the best cost-benefit ratio, due to the fact that they reduced the dimensionality of the data and had similar efficacy or, in some cases, superior to the control group.