Rough - Fuzzy reasoning for customized text information retrieval

Abstract

Due to the large repository of documents available on the web, users are usually inundated by a large volume of information most of which are found to be irrelevant. Since user perspectives vary, a client-side text filtering system that learns the user's perspective can reduce the problem of irrelevant retrieval. In this paper, we have provided the design of a customized text information filtering system which learns user preferences and uses a rough-fuzzy reasoning scheme to filter out irrelevant documents. The rough set based reasoning takes care of natural language nuances like synonym handling, very elegantly. The fuzzy decider provides qualitative grading to the documents for the user's perusal. We have provided the detailed design of the various modules and some results related to the performance analysis of the system.