Abstract：In real social networks, there are multiple relationships between users. The existing social recommendation algorithms only consider the impact of one relationship on the recommendation results. Based on the multi-subnet composited complex network model, different social relationships among users are introduced into the user feature matrix. In this paper, matrix factorization social recommendation algorithm based on multi-relationship is proposed. By analyzing the experimental results on two real datasets, the social matrix factorization recommendation method with multi-relationship has a significant improvement in recommendation accuracy compared with the traditional matrix factorization algorithm.
周双, 宾晟, 孙更新. 融合多关系的矩阵分解社会化推荐算法[J]. 复杂系统与复杂性科学, 2020, 17(1): 30-36.
ZHOU Shuang, BIN Sheng, SUN Gengxin. Matrix Factorization Social Recommendation Algorithm Based on Multiple Social Relationships. Complex Systems and Complexity Science, 2020, 17(1): 30-36.
[1]Lü L, Medo M, Chi H Y, et al. Recommender systems[J]. Physics Reports, 2012, 519(1):1-49. [2]Guo Q, Song W, Hou L, et al. Effect of the time window on the heat-conduction information filtering medel[J]. Physica A: Statistical Mechanics and Its Applications, 2014,401(5):15-21. [3]陈志敏, 李志强. 基于用户特征和项目属性的协同过滤推荐算法[J]. 计算机应用, 2011, 31(7):1748-1750. Chen Zhimin, Li Zhiqiang. Collaborative filtering recommendation algorithm based on user characteristics and item attributes[J]. Journal of Computer Applications,2011,31(7):1748-1750. [4]Deshpande M, Karypis G. Item-Based top-n, recommendation algorithms[J]. ACM Trans on Information Systems, 2004,22(1):143-177. [5]Konstan J A, Miller B N, Maltz D, et al. GroupLens: Applying collaborative filtering to usenet news. Communications of the ACM, 2000,40(3):77-87. [6]Koren Y, Bell R, Volinsky C. Matrix factorization techniques for recommender systems[J]. Computer, 2009,42(8):30-38. [7]Massa P, Avesani P. Trust-aware collaborativefiltering for recommender systems[C]//OTM confederated International Conferences "on the Move to Meaningful Internet Systems", Springer, Berlin, Heidelberg, 2004: 492-508. [8]Massa P, Avesani P. Trust-aware recommendersystems[C]//Proc of RecSys, New York, NY, USA, 2007. [9]Li W, Qi J, Yu Z, et al. A social recommendation method based on? trust propagation and singular value decomposition[J]. Journal of Intelligent & Fuzzy Systems, 2017, 32(1):807-816. [10] 邓小方, 钟元生, 吕琳媛, 等. 融合社交网络的物质扩散推荐算法[J]. 山东大学学报(理学版), 2017, 52( 3):51-59, 67. Deng Xiaofang, Zhong Yuansheng, Lü Linyuan, et al. Mass diffusion on coupled social networks[J].Journal of Shandong University(Natural Science), 2017, 52( 3):51-59, 67. [11] 郭兰杰, 梁吉业, 赵兴旺. 融合社交网络信息的协同过滤推荐算法[J]. 模式识别与人工智能, 2016, 29( 3):281-288. Guo Lanjie, Liang Jiye, Zhao Xingwang. Collaborative filtering recommendation algorithm incorporating social network information[J]. Pattern Recognition and Artificial Intelligence, 2016, 29(3):281-288. [12] 胡惠成, 陈平华. 一种融合隐式信任关系的推荐算法[J]. 广东工业大学学报, 2017, 34 (3): 43-48. Hu Huicheng, Chen Pinghua. Research on implicit trust relationship aware recommendation algorithm[J]. Journal of Guangdong University of Technology, 2016, 29( 3):281-288. [13] Mnih A, Salakhutdinov R. Probabilistic matrix factorization[C]// Advances in neural information processing systems, Vancouver, British Columbia, Canada, 2007: 1257-1264. [14] 郭宁宁, 王宝亮,侯永宏. 融合社交网络特征的协同过滤推荐算法[J]. 计算机科学与探索, 2018, 12(2):208-217. Guo Ningning,Wang Baoliang,Hou Yonghong,et al. Collaborative filtering recommendation algorithm based on characteristics of social network[J]. Journal of Frontiers of Computer Science and Technology, 2018, 12(2):208-217. [15] 隋毅.多子网复合复杂网络模型及其相关性质的研究[D]. 青岛:青岛大学,2012. Sui Yi. Research on multi-subnet composited complex network and its related properties [D]. Qingdao: Qingdao University, 2012. [16] Mao Y Y, Liu J X, Hu R, et al. Sigmoid function-basedWeb service collaborative filtering recommendation algorithm[J]. Journal of Frontiers of Computer Science andTechnology, 2017, 11(2): 314-322. [17] Ma H, Zhou D Y, Liu C, et al. Recommender systems with social regularization[C]// Proceedings of the Fourth ACM International Conference on Web Search and Data Mining, WSDM 2011, Hongkong, China, 2011: 287-296.
