An unified user dynamic interest description model

Abstract

The amount of information available world-wide and its network-based linkage will continue its rapid growth in the foreseeable future. It is urgent that we need a new retrieval mode to span the gap between information explosion and user requirement. This paper reports an user interest mining method based on cross-media and a unified model which describes user’s dynamic interest changing through time to overcome the contradiction between short-time interest and long-time interest description in traditional methods. We also present a developing personalized retrieval system FizZ which mines user’s interest by installing IE plug-in.