Abstract

An important yet difficult topic is the incorporation of semantic knowledge from ontology into categorical documents. In addition, there are many subjects listed on the Internet based on computers. The aim of this system is to group documents depending on the nature of the data tested and to describe the techniques of testing in detail. It also reports on studies carried out to test the weighting scheme used to encode the relevance of concepts in papers. The approach employed the Table of Categorical Information before clustering the document to keep information on the idea before the concept was weighted. For the analysis, the system must employ ontology to describe and organise information and to cluster it from heterogeneous sources.