Category Mapping for Integration of Web Shopping Search

Abstract

As there are more and more online stores and shopping sites available on the web, it becomes very time-consuming, if not impossible, to visit and search all the online stores and shopping sites to ¯nd the best product and store to buy. There is great need to build an integrated shop- ping search system that provides a uni¯ed in- terface and metasearch capability to search and access all the shopping sites in one query sub- mission. Observe that most of the online store and shopping sites provide a category directory and a query interface for users to ¯nd products of their interest. One usually navigates along the category directory to select a category, and then submits a query to ¯nd products in the selected category whose descriptions match the query. Automatic selection of categories from each shopping site is one of the fundamental problems to build an integrated shopping search systems. Note that category selection reduces the space to search, and improves the query time and quality of the query result. Quick and high quality response from each shopping site is very crucial to the performance of an integrated shop- ping search system. In this paper, we study the problem of automatic category selection. In particular, we study the problem of mapping cate- gories among shopping web sites. We formulate the mapping problem as a search problem, and present an efficient algorithm that aims to find the optimal mapping. Experiment shows that our approach performs very well.