A research paper recommender system based on spreading activation model

With the progress of digital technology and the development of the web, digital library need to provide on-line services to meet the diversified demands of individual patrons and to offer more personalized services. A personalized research paper recommender system is proposed in this paper. It constructs user profile based on concept tree to overcome the drawbacks of the traditional vector space model. A spreading activation model is employed to search for user community with similar interests. Finally, its accuracy and availability is verified based on data extracted from the database of National Science and Technology Library.