Visibility Graph and Diversity Based Hybrid Collaborative Filtering Recommendation

• 作 者: WangHong;SunYanShen;YuXiao-Mei;
• 机 构: 山东师范大学
• 出 处: 中国计算机学会多值逻辑与模糊逻辑专业委员会第十四届学术会议
• 发表日期: 2014年期

　　Many researchers have been attracted in personalized recommendation which is considered as one of the most effective implement to solve the problem of information overloading.We propose a hybrid collaborative filtering recommendation method based on the visibility graph and diversity in this paper.Firstly,we construct a personalized recommendation model based on frequent item mining and visibility graph,thus making us obtain user-item networks and user-user networks.Secondly,we define concepts of similarity and some similarity criteria and then we put forward and adjust recommendation algorithms in super-network model based on link mining and diversity.Finally,we apply our methods to classic Retail dataset in order to evaluate the performance of our algorithms.Experiment results show that our methods do better than traditional collaborative filtering and content based recommendation methods in Drecision.recall and time.