Improving Web Search using Trust and Social Networks
This event took place on Wednesday 25 October 2006 at 11:30

Tom Heath KMi, The Open University

Conventional search engines treat all users the same. Relevance is seen as a relationship between a query and a resource, ignoring aspects of the user's information need that are not explicit in the query. This contrasts with offline information seeking, where people frequently use social networks of known individuals as a source of information and as a basis for assessing its relevance. In this presentation I will outline our approach to personalised information seeking, based on computing trust relationships between the user and members of their social networks as a means to rank and filter resources. Results of an empirical study underlying this approach will be presented, followed by a demonstration of parts of the infrastructure through which our approach will be realised.