Online news recommendation systems aim to address the information explosion of news and make personalized recommendations for users. The key problem of personalized news recommendation is to model users' interests and track their changes. A common way to deal with the user modeling problem is to build user profiles from observed behavior. However, the majority of existing methods make static representations of user profiles and little research has focused on effective user modeling that could dynamically capture user interests in news topics. To address this problem, in this paper, we propose UP-TreeRec, a news recommendation framework based on a user profile tree(UP-Tree), which is a novel framework combining content-based and collaborative filtering techniques. First, by exploiting a novel topic model namely UILDA, we obtain the representation vectors for news content in a topic space as the fundamental bridge to associate user interests with news topics. Next, we design a decision tree with a dynamically changeable structure to construct a user interest profile from the user's feedback. Furthermore, we present a clustering-based multidimensional similarity computation method to select the nearest neighbor of the UP-Tree efficiently. We also provide a Map-Reduce framework-based implemen-tation that enables scaling our solution to real-world news recommendation problems. We conducted several experiments compared to the state-of-the-art approaches on real-world datasets and the experimental results demonstrate that our approach significantly improves accuracy and effectiveness in news recommendation.
展开▼
