A Personalized Recommendation Model Based on Social Tags

Abstract

In traditional e-commerce websites, social tags are used in product classification only, and not applied in the domain of personalized recommendation technology. In this paper, we propose a personalized recommendation model based on social tags. We build a user interest model for products by reflecting user interest and product features directly through social tags, and optimize the interest model by social tags clustering. We design a personalized recommendation algorithm based on this model in order to find out the high user interest degree products, which can provide personalized recommendation service for users. The experiment results show that the personalized recommendation model based on social tags can effectively improve the accuracy of product recommendation.