Web Page Enrichment using a Rough Set Based Method

Abstract

When documents are matched to a given query, often the terms in the query are matched to the words in the documents for calculating similarity. But it is a good idea if the given document is represented in an enriched manner with not only the actual words occurring in the document but also with the synonyms of the important words. This would definitely improve the recall of the system. With its ability to deal with vagueness and fuzziness, tolerance rough set seems to be promising tool to model relations between terms and documents. In many information retrieval problems, especially in text classification, determining the relation between term-term and term-document is essential. In this work, the application of TRSM to web page classification was evaluated to determine its effectiveness as a way to enrich a web page.