基于非负矩阵分解的群组推荐算法

计算机工程与科学 ›› 2022, Vol. 44 ›› Issue (05): 933-943.

基于非负矩阵分解的群组推荐算法

贾俊杰,姚叶旺,陈旺虎

(西北师范大学计算机科学与工程学院,甘肃兰州 730070)

收稿日期:2020-08-16 修回日期:2020-12-16 接受日期:2022-05-25 出版日期:2022-05-25 发布日期:2022-05-24
基金资助:
国家自然科学基金（61967013）；甘肃省高等学校创新能力提升项目（2019A-006）

A group recommendation algorithm based on non-negative matrix factorization

JIA Jun-jie,YAO Ye-wang,CHEN Wang-hu

(School of Computer Science and Engineering,Northwest Normal University,Lanzhou 730070,China)

Received:2020-08-16 Revised:2020-12-16 Accepted:2022-05-25 Online:2022-05-25 Published:2022-05-24

摘要/Abstract

摘要： 近年来，随着媒介技术的快速发展，人们成组活动的现象逐渐增多，群组推荐系统也逐渐受到关注。现有的群组推荐系统往往将不同的成员视为同质对象，忽视了成员专业背景和项目固有属性之间的关系，无法真正地解决融合过程中的偏好冲突问题。为此，提出一种基于非负矩阵分解的群组推荐算法，通过非负矩阵分解将群组评分信息分解为用户矩阵和项目矩阵，针对2个矩阵分别利用隶属度和专业度权值计算得到项目隶属度矩阵和成员专业度矩阵，并由此获得各成员在不同项目上的贡献度来构建群组偏好模型。实验结果表明，所提算法在不同群组规模和组内相似度的情况下依然具有较高的推荐准确度。

关键词: 群组推荐系统, 偏好融合, 非负矩阵分解, 贡献度

Abstract: In recent years, with the rapid development of media technology, the phenomenon of peoples group activities has gradually increased, and the group recommendation system has gradually attracted attention. Existing group recommendation systems often treat different members as homogeneous objects, ignoring the relationship between members professional backgrounds and inherent attri- butes of items, and cannot really solve the problem of preference conflicts in the fusion process. Therefore, a group recommendation algorithm based on non-negative matrix factorization is proposed. The algorithm decomposes the group rating information into the user matrix and the item matrix by non- negative matrix factorization. According to the two matrices, the item membership matrix and member professionalism matrix are calculated by using membership and professionalism weights respectively, and the contribution degree of each member on different items is obtained to construct the group prefe- rence model. The experimental results show that the proposed algorithm still has high recommendation accuracy in the case of different group size and intra-group similarity.

Key words: group recommendation system, preference aggregation, non-negative matrix factorization, contribution degree

贾俊杰, 姚叶旺, 陈旺虎. 基于非负矩阵分解的群组推荐算法[J]. 计算机工程与科学, 2022, 44(05): 933-943.

JIA Jun-jie, YAO Ye-wang, CHEN Wang-hu. A group recommendation algorithm based on non-negative matrix factorization[J]. Computer Engineering & Science, 2022, 44(05): 933-943.

参考文献［26］

［1］	Ricci F,Rokach L,Shapira B.Introduction to recommender systems handbook［M］∥Recommender Systems Handbook.Boston,MA:Springer,2011:1-35.
［2］	Tian Y,Zheng B,Wang Y,et al.College library personalized recommendation system based on hybrid recommendation algorithm［J］.Procedia CIRP,2019,83:490-494.
［3］	Breese J S,Heckerman D,Kadie C.Empirical analysis of predictive algorithms for collaborative filtering［J］.arXiv:1301.7363,2013.
［4］	Koren Y.Collaborative filtering with temporal dynamics［C］∥Proc of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining，2009:447-456.
［5］	Garcia I,Pajares S,Sebastia L,et al.Preference elicitation techniques for group recommender systems［J］.Information Sciences,2012,189:155-175.
［6］	Mahyar H, Ghalebi K E,Morshedi S M,et al.Centrality-based group formation in group recommender systems［C］∥Proc of the 26th International Conference on World Wide Web Companion,2017:1187-1196.
［7］	Agarwal A,Chakraborty M,Chowdary C R.Does order matter? Effect of order in group recommendation［J］.Expert Systems with Applications,2017,82:115-127.
［8］	Boratto L,Carta S,Fenu G.Discovery and representation of the preferences of automatically detected groups:Exploiting the link between group modeling and clustering［J］.Future Generation Computer Systems,2016,64:165-174.
［9］	Masthoff J.Group recommender systems:Aggregation,satisfaction and group attributes［M］∥Recommender Systems Handbook.Boston,MA:Springer,2015:743-776.
［10］	Chao D L,Balthrop J,Forrest S.Adaptive radio:Achieving consensus using negative preferences［C］∥Proc of the 2005 International ACM SIGGROUP Conference on Supporting Group Work,2005:120-123.
［11］	Chen Jun-tong,Gu Tian-long,Chang Liang,et al.A tourist group recommendation method combining collaborative filtering and user preferences［J］.CAAI Transactions on Intelligent Systems,2018,13(6):999-1005.(in Chinese)
［12］	Tao Yong-cai,Ding Xin,Shi Lei,et al.Group POI recommendation model based on the user check-in behavior［J］.Journal of Chinese Computer Systems,2018,39(10):2260-2265.(in Chinese)
［13］	Hu Chuan,Meng Xiang-wu,Zhang Yu-jie,et al.Enhanced group recommendation method based on preference aggregation［J］.Journal of Software,2018,29(10):3164-3183.(in Chinese)
［14］	Zheng Wei,Li Bo-han,Wang Ya-nan,et al.Group recommendation algorithm model combined with preference interaction［J］.Journal of Chinese Computer Systems,2018,39(2):372-378.(in Chinese)
［15］	Wang X,Su L,Zhou Q,et al.Group recommender systems based on members’ preference for trusted social networks［J］.Security and Communication Networks,2020,2020:Article ID 1924140.
［16］	Koren Y,Bell R,Volinsky C.Matrix factorization techniques for recommender systems［J］.Computer,2009,42(8):30-37.
［17］	Wang Hai-yan,Dong Mao-wei.Latent group recommendation based on dynamic probabilistic matrix factorization model integrated with CNN［J］.Journal of Computer Research and Development,2017,54(8):1853-1863.(in Chinese)
［18］	Wang Gang,Jiang Jun,Wang Han-ru,et al.Study of group recommendation based on probabilistic matrix factorization［J］.Chinese Journal of Computers,2019,42(1):98-110.(in Chinese)
［19］	Ortega F,Hernando A,Bobadilla J,et al.Recommending items to group of users using matrix factorization based collaborative filtering［J］.Information Sciences,2016,345:313-324.
［20］	Zhang S, Hu Q.Research of group recommendation based on matrix factorization［C］∥Proc of 2019 Chinese Control and Decision Conference(CCDC),2019:3736-3739.
［21］	Wang W,Zhang G,Lu J.Member contribution-based group recommender system［J］.Decision Support Systems,2016,87:80-93.
［22］	Lee D D,Seung H S.Learning the parts of objects by non-negative matrix factorization［J］.Nature,1999,401(6755):788-791.
［23］	Li Le,Zhang Yu-jin.A survey on algorithms of non-negative matrix factorization［J］.Acta Electronica Sinica,2008,36(4):737-743.(in Chinese)
［24］	Lee D D,Seung H S.Algorithms for non-negative matrix factorization［J］.Advances in Neural Information Processing Systems,2000,13:556-562.
［25］	Boratto L,Carta S,Satta M.Groups identification and individual recommendations in group recommendation algorithms［C］∥Proc of Conference on Practical Use of Recommender Systems, Algorithms and Technologies,2010:27-34.
［26］	Zhang Yu-jie,Du Yu-lu,Meng Xiang-wu.Research on group recommender systems and their applications［J］.Chinese Journal of Computers,2016,39(4):745-764.(in Chinese)
	附中文参考文献：
［11］	陈君同,古天龙,常亮,等.融合协同过滤与用户偏好的旅游组推荐方法［J］.智能系统学报,2018,13(6):999-1005.
［12］	陶永才,丁鑫,石磊,等.基于用户签到行为的群组兴趣点推荐模型［J］.小型微型计算机系统,2018,39(10):2260-2265.
［13］	胡川,孟祥武,张玉洁,等.一种改进的偏好融合组推荐方法［J］.软件学报,2018,29(10):3164-3183.
［14］	郑伟,李博涵,王雅楠,等.融合偏好交互的组推荐算法模型［J］.小型微型计算机系统,2018,39(2):372-378.
［17］	王海艳,董茂伟.基于动态卷积概率矩阵分解的潜在群组推荐［J］.计算机研究与发展,2017,54(8):1853-1863.
［18］	王刚,蒋军,王含茹,等.基于联合概率矩阵分解的群推荐方法研究［J］.计算机学报,2019,42(1):98-110.
［23］	李乐,章毓晋.非负矩阵分解算法综述［J］.电子学报,2008,36(4):737-743.
［26］	张玉洁,杜雨露,孟祥武.组推荐系统及其应用研究［J］.计算机学报,2016,39(4):745-764.

[1]	任重鲁，李金明. 非负矩阵分解在微阵列数据分类和聚类发现中的应用[J]. J4, 2014, 36(07): 1389-1397.
[2]	石金龙,骆志刚. 非负矩阵分解算法及其在生物信息学中的应用研究[J]. J4, 2010, 32(8): 117-123.
[3]	晁永国. 一种改进的非负稀疏编码图像编码方案[J]. J4, 2010, 32(10): 66-68.