A Semantic Concept Operation Based on Fuzzy Document Ordering System and its Application to Reuter Database

摘要

A fuzzy document ordering system (FOCUS) with a shrink operation is proposed to classify vast unknown documents on the Worldwide Web by changing the user's viewpoint in hierarchical semantic concept structures. The shrink operation, a FOCUS semantic concept, is defined based on the user's preference vector space and its hierarchical semantic concept structures developed using the concept System Dictionary (CSD) of the Japan Electronic Dictionary Research Institute (EDR). We demonstrate the effectiveness of the shrink operation in document ordering experiments by 5 subjects a using 20 known and 40 unknown documents extracted from the Reuter-21578 Database, i.e., shrinkage of the user's preference vector space. We confirmed that precision obtained by FOCUS with the shrink operation exceeds that obtained by the conventional method without the shrink operation by over 20%. Processing time by our proposal is just 1/18 that of the conventional method (Pentium III, 550 MHz, Memory 256 MB).