Hierarchical classification as an aid to database and hit-list browsing

Authors:
J. Royce Rose;Johann Gasteiger
Affiliations:
Department of Computer Science, The University of South Carolina, Columbia, South Carolina;Computer-Chemie-Centrum, Universitaet Erlangen-Nuernberg, Naegelsbachstrasse 25, D-91052 Erlangen, Germany
Venue:
CIKM '94 Proceedings of the third international conference on Information and knowledge management
Year:
1994

Citing 4
Cited 2

CASREACT: more than a million reactions

Journal of Chemical Information & Computer Sciences
Building and refining a knowledge base for synthetic organic chemistry via the methodology of inductive and deductive machine learning

Journal of Chemical Information & Computer Sciences
Ordering effects in clustering

ML92 Proceedings of the ninth international workshop on Machine learning
Knowledge Discovery in Databases

Knowledge Discovery in Databases

Dynamic and efficient key management for access hierarchies

Proceedings of the 12th ACM conference on Computer and communications security
Key management for non-tree access hierarchies

Proceedings of the eleventh ACM symposium on Access control models and technologies

Quantified Score

Hi-index	0.00

Visualization

Abstract

A navigational aid for databases that relies on unsupervised hierarchical classification is presented. The approach to hierarchical classification, based on both functional and topological features, supports the creation of deep hierarchies in which succeeding levels represent increasing degrees of abstraction. This allows the user to quickly evaluate the result of a query and to locate interesting items and classes of items by performing a tree traversal rather than a sequential perusal of a hit list or a series of ad hoc query refinements. In very large databases where classical querying methods are increasingly inadequate such as chemical reaction databases, such a browsing method is required in order to manage the flood of information with which the user is confronted.