Journal of Computer Applications ›› 2018, Vol. 38 ›› Issue (9): 2523-2528.DOI: 10.11772/j.issn.1001-9081.2018030683

Previous Articles     Next Articles

Regularized matrix decomposition recommendation model integrating social networks and interest correlation

WEN Kai1,2, ZHU Chuanliang1   

  1. 1. Research Center of New Telecommunication Technology Applications, Chongqing University of Posts and Telecommunications, Chongqing 400065, China;
    2. Chongqing Information Technology Designing Company Limited, Chongqing 401121, China
  • Received:2018-04-03 Revised:2018-04-26 Online:2018-09-10 Published:2018-09-06
  • Contact: 朱传亮


文凯1,2, 朱传亮1   

  1. 1. 重庆邮电大学 通信新技术应用研究中心, 重庆 400065;
    2. 重庆信科设计有限公司, 重庆 401121
  • 通讯作者: 朱传亮
  • 作者简介:文凯(1972—),男,重庆人,高级工程师,博士,主要研究方向:移动通信、数据挖掘;朱传亮(1994—),男,湖北武汉人,硕士研究生,CCF会员,主要研究方向:推荐系统、数据挖掘。

Abstract: In view of the fact that users' preferences and social interaction data are very sparse, and the fact that users may prefer products recommended by friends than recommended by foes, a regularized matrix decomposition recommendation algorithm integrating with social network and interest preference similarity was proposed. First of all, for the problem of sparse data of social relations. Global and local topological characteristics of the network were used to extract trust and distrust matrices between users respectively. Secondly, a method for calculating interest preference similarity between users was defined. Finally, in the process of matrix decomposition, the trust matrix, the distrust matrix, and the interest correlation were synthetically taken into consideration to make recommendations for the users. Experiments show that this method is superior to other regularization recommendation methods. Compared with the basic matrix decomposition model (SocialMF), SoRec, TrustMF, CTRPMF and RecSSN algorithm, the proposed algorithm reduces 1.1% to 9.5% and 2% to 10.1% respectively in the root mean square error (RMSE) and the mean absolute error (MAE), improved recommendations effectively.

Key words: data sparsity, recommendation system, social network, preference similarity, matrix factorization, regularization

摘要: 针对目前用户偏好数据和社交关系数据十分稀疏的问题,以及用户可能更加喜欢朋友推荐的商品而不喜欢非朋友推荐的商品这样一个事实,提出了一种结合社交网络和用户间的兴趣偏好相似度的正则化矩阵分解推荐算法,首先针对社交关系数据稀疏问题,利用网络的全局和局部拓扑特性挖掘出用户间的信任和不信任关系矩阵,然后定义了一种改进的用户间的兴趣偏好相似度计算方法,最后在矩阵分解的过程中将信任矩阵、不信任矩阵以及兴趣相关性综合起来为用户作出推荐。实验表明该方法优于主要的正则化推荐方法,与基本的矩阵分解模型(SocialMF)、SoRec、TrustMF、CTRPMF、RecSSN算法相比,算法在均方根误差(RMSE)和平均绝对误差(MAE)上分别减小了1.1%~9.5%和2%~10.1%,取得了较好的推荐效果。

关键词: 数据稀疏, 推荐系统, 社交网络, 偏好相似度, 矩阵分解, 正则化

CLC Number: