Abstract

A framework for recommendation of multimedia objects based on processing of individual ontologies is proposed in the chapter. The recommendation process takes into account similarities calculated both between objects' and users' ontologies, which reflect the social and semantic features existing in the system. The ontologies, which are close to the current context, provide a list of suggestions presented to the user. Each user in the system possesses its own Personal Agent that performs all necessary online tasks. Personal Agents co-operate each other and enrich lists of possible recommendations. The system was developed for the use inthe Flickr multimedia sharing system.