With the development of personalized services, collaborative filtering techniques have been successfully applied to the network recommendation system. But sparse data seriously affect the performance of collaborative filtering algorithms. To alleviate the impact of data sparseness, using user interest information, an improved user-based clustering Collaborative Filtering (CF) algorithm is proposed in this paper, which improves the algorithm by two ways: user similarity calculating method and user-item rating matrix extended. The experimental results show that the algorithm could describe the user similarity more accurately and alleviate the impact of data sparseness in collaborative filtering algorithm. Also the results show that it can improve the accuracy of the collaborative recommendation algorithm.