一种基于时间和标签上下文的协同过滤推荐算法  

A Collaborative Filtering Recommendation Algorithm Based on the Context of Time and Tags

作　　者：窦羚源 王新华[1,2] 

机构地区：[1]山东师范大学信息科学与工程学院,济南250014 [2]山东省分布式计算机软件新技术重点实验室,济南250014

出　　处：《太原理工大学学报》2015年第6期735-740 748,共7页Journal of Taiyuan University of Technology

基　　金：山东省优秀中青年科学家科研奖励基金项目:城市车辆无线传感器网络信息感知和分发关键技术研究(2010BSE14022)

摘　　要：针对常规推荐算法数据单一、准确性和可靠性都比较低的问题,提出了将时间和标签上下文信息加入到推荐算法中,以丰富单个用户或商品的信息。利用时间信息挖掘用户间的影响关系,同时利用标签上下文来衡量物品间的关系,最后将用户关系向量和物品关系向量融合到概率矩阵分解模型中。实验结果表明,提出的协同过滤推荐算法能够提高推荐的准确性和精度。The conventional recommendation algorithms only take the user-item ratings into account.Because of the lack in data type,the accuracy and reliability of the algorithms are relatively low.In this paper we add the time and tag context information to the recommendation algorithm,in order to enrich the individual user or commodity information.The time context is used to mine the influence relationship between users and the tag context is used to measure the relationship between items at the same time.Finally we fuse user relation vector and item relation vector to the probabilistic matrix factorization model.The experimental results show that the proposed collaborative filtering algorithm in this paper can improve the accuracy and precision of recommendation.

关 键 词：推荐系统 概率矩阵分解 时间上下文 标签上下文 

分 类 号：TP391.3[自动化与计算机技术—计算机应用技术]