A Personalization layer for mediation systems

Mediation systems allow integration of disparate and heterogeneous data sources. Unfortunately, with the increasing number of integrated sources, especially in the context of web, mediator's responses time increases considerably while the answers are not adapted to users profiles. In this paper, we present a personalization layer that makes the mediation system more sensitive to user's preferences. The layer sits between the user and the mediation system. It captures the user profile and performs a smart source selection according to user's interests and quality preferences. Selection is based on similarity measurement between users and sources models. Our solution for personalizing data source selection provides the mediator with a set of relevant data sources. These are then involved in the rewriting process to give more satisfying response.