Regensburg 2007 – scientific programme

Parts | Days | Selection | Search | Downloads | Help

AKSOE: Arbeitskreis Physik sozio-ökonomischer Systeme

AKSOE 12: Social, Information-, and Production Networks III

AKSOE 12.2: Talk

Thursday, March 29, 2007, 10:45–11:15, H8

A Trust-based Recommendation System on a Social Network — •Stefano Battiston, Frank Walter, and Frank Schweitzer — Chair of Systems Design, ETH Zurich, Kreuzplatz 5, 8032 Zurich, Switzerland

Recommender systems are today widely spreading in web services. They are mostly based on centralized collaborative filtering, where an agent is recommended items which were chosen by other agents similar to her. In contrast, we present a model of a recommendation system based on trust relationships among agents of a social network. Trust evolves in time through a learning process and as a result agents can use their social network to reach information and their trust relationships to filter it. We identify the impact of network density, preference heterogeneity among agents, and knowledge sparseness on the performance of the system. We demonstrate that the system selforganises into a state close to the optimum. This is an emergent property of the system, achieved without explicit coordination from the local interactions of the agents.