Using Defeasible Logic Programming with Contextual Queries for Developing Recommender Servers
Mariano Tucat, Alejandro Javier García, Guillermo Ricardo Simari · 2009
In this work we introduce a defeasible logic programming recommender server that accepts different types of queries from client agents that can be distributed in remote hosts. We formalize new ways of querying recommender servers con-taining specific information or preferences, and creating a particular context for the queries. This special type of queries (called contextual queries) allows recommender servers to compute recommendations for any client using its prefer-ences, and will be answered using an argumentative inference mechanism. We focus on a particular implementation of rec-ommended systems that extends the integration of argumen-tation and recommender systems to a multi-agent setting. Our approach is based on a DeLP-server that can answer queries from agents in remote hosts. Since client agents can consult different domain specific recommender servers, then, multi-ple configurations of clients and servers can be defined.