点击次数：

论文类型：会议论文

发表时间：2011-03-09

收录刊物：EI、CPCI-S、Scopus

卷号：186

页面范围：621-625

关键字：personalized filtering; collaborative filtering; collaborative tagging; tag

摘要：Recommendation algorithms suffer the quality from the huge and sparse dataset. Memory-based collaborative filtering method has addressed the problem of sparsity by predicting unrated values. However, this method increases the computational complexity, sparsity and expensive complexity of computation are trade-off. In this paper, we propose a novel personalized filtering (PF) recommendation algorithm based on collaborative tagging, which weights the feature of tags that show latent personal interests and constructs a top-N tags set to filter out the undersized and dense dataset. The PF recommendation algorithm can track the changes of personal interests, which is an untilled field for previous studies. The results of empirical experiments show that the sparsity level of PF recommendation algorithm is much lower, and it is more computationally economic than previous algorithms.