Providing metrics and automatic enhancement for hierarchical taxonomies

  • Authors:

  • Ghassan Beydoun;Francisco GarcíA-SáNchez;Cristin M. Vincent-Torres;Antonio A. Lopez-Lorca;Rodrigo MartíNez-BéJar

  • Affiliations:

  • School of Information Systems and Technology, University of Wollongong, NSW 2522, Australia;Faculty of Computer Science, University of Murcia, Murcia, Spain;Faculty of Computer Science, University of Murcia, Murcia, Spain;School of Information Systems and Technology, University of Wollongong, NSW 2522, Australia;Faculty of Computer Science, University of Murcia, Murcia, Spain

  • Venue:
  • Information Processing and Management: an International Journal
  • Year:
  • 2013

Quantified Score

Hi-index 0.00

Visualization

Abstract

Taxonomies enable organising information in a human-machine understandable form, but constructing them for reuse and maintainability remains difficult. The paper presents a formal underpinning to provide quality metrics for a taxonomy under development. It proposes a methodology for semi-automatic building of maintainable taxonomies and outlines key features of the knowledge engineering context where the metrics and methodology are most suitable. The strength of the approach presented is that it is applied during the actual construction of the taxonomy. Users provide terms to describe different domain elements, as well as their attributes, and methodology uses metrics to assess the quality of this input. Changes according to given quality constraints are then proposed during the actual development of the taxonomy.