Collaborative filtering towards distributed work/learning environment

Nowadays, enormous amounts of on-line information, for example World-Wide Web documents and netnews articles, are available on the Internet, so we can get useful pieces of information through the network. In particular, there are large amounts of raw resources useful for teaching/learning. However at present, these resources are underutilized, because df the situation called information flood. The purpose of this study is to develop a collaborative filtering system, where collaboration among group members are implicitly incorporated into the process of information gathering. In the architecture, we propose two types of software agents and the task of filtering is accomplished by cooperative behavior of multi-agent. In this paper, we describe the concept of our collaborative filtering and the representation of personal information interests and its acquisition method.