On N-layer Vector Space Model-Based Web Information Retrieval

Abstract

A new model of information retrieval algorithms, N-layer vector space model, is proposed in this paper based on the traditional vector space model. When it is used in Web information-retrieval, we have improved the representation of text vector and the statistics of feature items frequency and thus make it better suit the dynamic expansion of the document set. The experiment result shows that this method can further improve the performance of vector space model, save storage space, and speed up the retrieval speed with high precision and recall rate.