Interest clustering techniques for efficient event routing in large-scale settings

The publish/subscribe interaction paradigm is today becoming mainstream in a large number of very large scale applications like news syndication (with RSS) or massive multiplayer games. These applications are often still implemented by means of centralized services that will hardly scale with the user growth expected in the next years. Modern publish/subscribe systems are striving to address these scalability needs to play a dominant role in this future market. A very important contribution, on the road to reach this goal, is given by the interest clustering techniques adopted by these systems. Interest clustering aims at putting in close applicative relationship groups of users sharing similar interests in order to reduce the effort needed to dispatch a message to group. This technique can be applied to event dissemination mechanisms based on filtering to reduce the total amount of messages generated during event routing and, consequently, improve the overall system performance. In this paper we explore this topic to discover the potentialities of interest clustering, to understand how it can be implemented in a publish/subscribe system, and to study, through a small focussed survey, the central role played by this technique in modern systems. Copyright 2008 ACM.