Abstract
With the rapid growth of the amount of information stored on networks such as the internet, it is more difficult for information seekers to retrieve relevant information. This paper illustrates the design and improvement of a near neighborhood approach of information retrieval system to facilitate domain specific search. In exacting, a novel model depending on the notion of neighborhood system designed to rank documents according the searchers specific granularity requirements. The initial experiments confirm that our approach outperforms a classical vector-based information retrieval system. Our research work opens the door to the design and development of the next generation of internet search engines to alleviate the problem of information overload using more topological concepts.