Agent-community-based peer-to-peer information retrieval and its evaluation

Tsunenori Mine, Akihiro Kogo, Makoto Amamiya

Abstract: The Agent-Community-based Peer-to-Peer (ACP2P) information retrieval method uses agent communities to manage and look up information of interest to users. An agent works as a delegate of its user and searches for information that the user wants by communicating with other agents. The communication between agents is carried out in a peer-to-peer computing architecture. Retrieving information relevant to a user query is performed with content files which consist of original and retrieved documents, and two histories: a query/retrieved document history and a query/sender agent history. Making use of the histories has a collaborative filtering effect, which gradually creates virtual agent communities, where agents with the same interests stay together. Our hypothesis is that a virtual agent community reduces communication loads necessary to perform a search. As an agent receives more queries, then more links to new knowledge are acquired. From this behavior, a “give-and-take” (or positive feedback) effect for agents seems to emerge. However, we have only shown parts of the effects of reducing communication loads and making “give-and-take” through preliminary experimental results.