Using Dictionaries for Biomedical Text Classification

  • R. Romero
  • E. L. Iglesias
  • L. Borrajo
  • C. M. Redondo Marey
Part of the Advances in Intelligent and Soft Computing book series (AINSC, volume 93)

Abstract

The purpose of this paper is to study the use of dictionaries in the classification of biomedical texts. Experiments are conducted with three different dictionaries (BioCreative [13], NLPBA [8] and a subset of the UniProt database [4], named Protein) and three types of classifiers (KNN, SVM and Naive-Bayes) when they are applied to search on the PubMed database. Dictionaries have been used during the preprocessing and annotation of documents. The best results were obtained with the NLPBA and Protein dictionaries and the SVM classifier.

Keywords

Biomedical text mining classification techniques dictionaries 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • R. Romero
    • 1
  • E. L. Iglesias
    • 1
  • L. Borrajo
    • 1
  • C. M. Redondo Marey
    • 2
  1. 1.Univ. of VigoOurenseSpain
  2. 2.Complexo HospitalarioUniversitario de VigoVigoSpain

Personalised recommendations