Domain knowledge to support the discovery process: taxonomies

Authors:
Willi Klösgen
Affiliations:
Principal Researcher, Fraunhofer Institute for Autonomous Intelligent Systems, Sankt Augustin, Germany
Venue:
Handbook of data mining and knowledge discovery
Year:
2002

Citing 2
Cited 0

Explora: a multipattern and multistrategy discovery assistant

Advances in knowledge discovery and data mining
Finding Spatial Clusters

PKDD '97 Proceedings of the First European Symposium on Principles of Data Mining and Knowledge Discovery

Quantified Score

Hi-index	0.00

Visualization

Abstract

We classify methods for generating taxonomies and study the role of taxonomies in the knowledge discovery in databases (KDD) process. First, we summarize methods for generating taxonomies for the values in the domain of a single attribute. We classify these methods using several dimensions, such as scale of the attribute, supervised versus unsupervised, dynamic versus static, and top-down versus bottom-up methods. Then we analyze the role of taxonomies in the KDD process by discussing for which tasks they are important, how they are used for discovery, and the advantages of using such taxonomies.