A SAM-Based Evolution Model of Ontological User Model

The goal of user modeling is to provide personalized services based on userpsilas interests and preferences, thus allowing for more efficient information access. Frequently userpsilas interests drift with time. The ability to adapt fast to the current user´s interests is an important feature of user model. In this paper, based on behavioral psychology, a SAM (Spreading Activation Model)-based evolution model of ontological user model is proposed. The method utilizes semantic technology to adapt user model with the support of domain ontology. A spreading activation algorithm is used to maintain the interest weights based on the userpsilas ongoing behaviors. In the end, the SAM-based evolution model is applied in a computer science paper retrieval system (CSPRS). The result shows that the precision and recall of the retrieval system are improved obviously, and the SAM-based model is effective and efficient in the user model evolution.