Hierarchical Concept Structures Based Data Retrieval/Mining by Fuzzy Document Ordering System

Tadashi Ohashi, Hajime Nobuhara, and Kaoru Hirota

Tokyo Institute of Technology, G3-49, 4259 Nagatsuta, Midori-ku, Yokohama 226-8502, Japan

Received:

August 30, 2004

Accepted:

September 8, 2004

Published:

November 20, 2004

Keywords:

data mining, semantic concept, fuzzy, vector space model

Abstract

A shrink operation for FOCUS (Fuzzy dOCUment ordering System) is proposed as a tool for changing user’s viewpoint in concept structures of documents. The FOCUS produces the user’s preference vector space and its concept hierarchical structure based on CSD (Concept System Dictionary) produced by EDR (Japan Electronic Dictionary Research Institute). Through document ordering experiments by 5 examinees using 20 given documents and 40 unknown ones extracted from IMDB (Internet Movie Data Base), the effectiveness of shrink operations, i.e., shrinkage of user’s preference vector space, is confirmed in the way that it avails to do fuzzy document matching in user’s rough point of view by using the hierarchical structure.

Cite this article as:

T. Ohashi, H. Nobuhara, and K. Hirota, “Hierarchical Concept Structures Based Data Retrieval/Mining by Fuzzy Document Ordering System,” J. Adv. Comput. Intell. Intell. Inform., Vol.8 No.6, pp. 633-638, 2004.

Data files:

This article is published under a Creative Commons Attribution-NoDerivatives 4.0 Internationa License.