一种面向用户偏好定向挖掘的协同过滤个性化推荐算法

doi:10.11925/infotech.1003-3513.2014.06.04

摘要
参考文献
相关文章
Metrics

全文: PDF(505 KB) HTML
输出: BibTeX | EndNote (RIS)

摘要

[目的]解决协同过滤推荐的可扩展性问题和数据稀疏性问题。[方法]提出一种面向用户偏好定向挖掘的协同过滤算法。该算法以时间为约束，第一阶段先寻找基于项目的弱相似用户；第二阶段基于用户关联性和属性相似性进行定向挖掘，形成推荐集合。[结果]实验结果表明，新算法的时间复杂度降低一个数量级，并且数据越稀疏，推荐精度的领先优势越大。[局限]该算法基于用户已表现出的偏好进行深度推荐，对未表现出的其他偏好暂未涉及。[结论]该算法在提升可扩展性的同时，对数据稀疏性也有很强的适应能力。

	服务

	把本文推荐给朋友
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	宋梅青
	王伟军

关键词 ：协同过滤, 用户偏好, 个性化推荐, 推荐算法

Abstract：

[Objective] To solve the scalability problem and data sparsity problem of the collaborative filtering. [Methods]This paper proposes an algorithm of collaborative filtering personalized recommendation through directionally mining users' preferences. Introducing time as a variable, the algorithm excavates in two stages. The first stage is to find the project-based weak similar users, the second stage is to use users' relevance and attribute similarity so as to do directional excavation and form a collection of recommendation. [Results]Experimental results show that the time complexity of the new algorithm reduces a magnitude. Furthermore, the more sparser the data is, the greater leading advantage the recommendation accuracy has. [Limitations] The algorithm recommends deeply by analyzing the users' existed preferences, and it doesn't involve the users' preferences which haven't appeared. [Conclusions]This algorithm has a strong ability to adapt to data sparsity and enhances its scalability at the same time.

Key words： Collaborative filtering User preferences Personalized recommendation Recommendation algorithm

收稿日期: 2013-12-23

G202

基金资助:

本文系国家自然科学基金项目“基于用户偏好感知的SaaS 服务选择优化研究”（项目编号： 71271099）和湖北省自然科学基金创新群体重点项目“基于云计算的知识集成与服务研究”（项目编号： 2011CDA116）的研究成果之一。

通讯作者: 宋梅青E-mail：mqsong99@126.com E-mail: mqsong99@126.com

作者简介: 作者贡献声明：王伟军：确定研究方向及研究方法，提出论文的修订意见；宋梅青：进行算法设计及实验分析，负责论文的撰写与修订。

引用本文:

王伟军, 宋梅青. 一种面向用户偏好定向挖掘的协同过滤个性化推荐算法[J]. 现代图书情报技术, 2014, 30(6): 25-32.
Wang Weijun, Song Meiqing. A Collaborative Filtering Personalized Recommendation Algorithm Through Directionally Mining Users’ Preferences. New Technology of Library and Information Service, DOI：10.11925/infotech.1003-3513.2014.06.04.

链接本文:

http://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/10.11925/infotech.1003-3513.2014.06.04

[1] 项亮. 推荐系统实践[M]. 北京: 人民邮电出版社, 2012: 4-47. (Xiang Liang. Recommendation System Practice[M]. Beijing: Posts & Telecom Press, 2012:4-47.)
[2] Sarwar B M. Sparsity, Scalability, and Distribution in Recommender Systems[D]. Minneapolis, USA: University of Minnesota, 2001.
[3] Sarwar B M, Karypis G, Konstan J, et al. Recommender Systems for Large-scale E-commerce: Scalable Neighborhood Formation Using Clustering[C]. In: Proceedings of the 5th International Conference on Computer and Information Technology. 2002.
[4] Rashid A M, Lam S K, Karypis G, et al. ClustKNN: A Highly Scalable Hybrid Model-&Memory-based CF Algorithm[C]. In: Proceedings of the KDD Workshop on Web Mining and Web Usage Analysis, at 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2006.
[5] 王卫平, 寇艳艳. 基于AntStream用户聚类的协同过滤推荐系统[J]. 计算机系统应用, 2010, 19(12):180-184.(Wang Weiping, Kou Yanyan. Collaborative Filtering Recommender Systems Based on Clustered Users Using AntStream Algorithm[J]. Computer Systems & Applications, 2010, 19(12):180-184.)
[6] 邓爱林, 左子叶, 朱扬勇. 基于项目聚类的协同过滤推荐算法[J]. 小型微型计算机系统, 2004, 25(9): 1665-1670. (Deng Ailin, Zuo Ziye, Zhu Yangyong. Collaborative Filtering Recommendation Algorithm Based on Item Clustering[J]. Mini-Micro Systems, 2004, 25(9): 1665-1670.)
[7] 卞艺杰, 陈超, 马玲玲, 等. 一种改进的LSH/MinHash协同过滤算法[J]. 计算机与现代化, 2013(12): 19-22, 26. (Bian Yijie, Chen Chao, Ma Lingling, et al. An Improved LSH/MinHash Collaborative Filtering Algorithm[J]. Computer and Modernization, 2013(12): 19-22, 26.)
[8] 顾晔, 吕红兵. 改进的增量奇异值分解协同过滤算法[J]. 计算机工程与应用, 2011, 47(11): 152-154. (Gu Ye, Lv Hongbing. Improved Algorithm of Incremental Singular Value Decomposition Collaborative Filtering[J]. Computer Engineering and Applications, 2011, 47(11): 152-154.)
[9] 杨兴耀, 于炯, 吐尔根·依布拉音, 等. 融合奇异性和扩散过程的协同过滤模型[J]. 软件学报, 2013, 24(8): 1868-1884. (Yang Xingyao, Yu Jiong, Turgun Ibrahimi, et al. Collaborative Filtering Model Fusing Singularity and Diffusion Process[J]. Journal of Software, 2013, 24(8): 1868-1884.)
[10] Rennie J D M, Srebro N. Fast Maximum Margin Matrix Factorization for Collaborative Prediction[C]. In: Proceedings of the 22nd International Conference on Machine Learning. New York: ACM Press, 2005: 713-719.
[11] Goldberg K, Roeder T, Gupta D, et al. Eigentaste: A Constant Time Collaborative Filtering Algorithm[J]. Information Retrieval, 2001, 4(2):133-151.
[12] Kim D, Yum B J. Collaborative Filtering Based on Iterative Principal Component Analysis[J]. Expert Systems with Applications, 2005, 28(4): 823-830.
[13] 郁雪, 李敏强. 基于局部主成分分析的协同过滤推荐模型[J]. 计算机工程, 2010, 36(14): 37-39. (Yu Xue, Li Minqiang. Collaborative Filtering Recommendation Model Based on Local Principle Component Analysis[J]. Computer Engineering, 2010, 36(14): 37-39.)
[14] 罗辛, 欧阳元新, 熊璋, 等. 通过相似度支持度优化基于K近邻的协同过滤算法[J]. 计算机学报, 2010, 33(8): 1438-1445. (Luo Xin, Ouyang Yuanxin, Xiong Zhang, et al. The Effect of Similarity Support in K-Nearest-Neighborhood Based Collaborative Filtering[J]. Chinese Journal of Computers, 2010, 33(8): 1438-1445.)
[15] 郭艳红. 推荐系统的协同过滤算法与应用研究[D]. 大连:大连理工大学, 2008.(Guo Yanhong. On Collaborative Filtering Algorithm and Applications of Recommender Systems[D]. Dalian: Dalian University of Technology, 2008.)
[16] 孙小华. 协同过滤系统的稀疏性与冷启动问题研究[D]. 杭州: 浙江大学, 2005. (Sun Xiaohua. Research of Sparsity and Cold Start Problem in Collaborative Filtering[D]. Hangzhou: Zhejiang University, 2005.)
[17] 邓爱林, 朱扬勇, 施伯乐. 基于项目评分预测的协同过滤推荐算法[J]. 软件学报, 2003, 14(9):1621-1628.(Deng Ailin, Zhu Yangyong, Shi Bole. A Collaborative Filtering Recommendation Algorithm Based on Item Rating Prediction [J]. Journal of Software, 2003, 14(9): 1621-1628.)
[18] 李华, 张宇, 孙俊华. 基于用户模糊聚类的协同过滤推荐研究[J]. 计算机科学, 2012, 39(12): 83-86. (Li Hua, Zhang Yu, Sun Junhua. Research on Collaborative Filtering Recommendation Based on User Fuzzy Clustering[J]. Computer Science, 2012, 39(12): 83-86.)
[19] 邓晓懿, 金淳, 韩庆平, 等. 基于情境聚类和用户评级的协同过滤推荐模型[J]. 系统工程理论与实践, 2013, 33(11): 2945-2953. (Deng Xiaoyi, Jin Chun, Han Jim C, et al. Improved Collaborative Filtering Model Based on Context Clustering and User Ranking[J]. Systems Engineering——Theory & Practice, 2013, 33(11): 2945-2953.)
[20] 俞琰, 邱广华. 融合社会网络的协同过滤推荐算法研究[J].现代图书情报技术, 2012(6): 54-59. (Yu Yan, Qiu Guanghua. Research on Collaborative Filtering Recommendation Algorithm by Fusing Social Network[J]. New Technology of Library and Information Service, 2012(6): 54-59.)
[21] 林耀进, 胡学钢, 李慧宗. 基于用户群体影响的协同过滤推荐算法[J]. 情报学报, 2013, 32(3): 299-305. (Lin Yaojin, Hu Xuegang, Li Huizong. Collaborative Filtering Recommendation Algorithm Based on User Group Influence[J]. Journal of the China Society for Scientific and Technical Information, 2013, 32(3): 299-305.)
[22] 张海燕, 丁峰, 姜丽红. 基于模糊聚类的协同过滤推荐方法[J]. 计算机仿真, 2005, 22(8): 144-147. (Zhang Haiyan, Ding Feng, Jiang Lihong. A Collaborative Filtering Recommendation Method Based on Fuzzy Clustering[J]. Computer Simulation, 2005, 22(8): 144-147.)
[23] 韦素云, 业宁, 朱健, 等. 基于项目聚类的全局最近邻的协同过滤算法[J]. 计算机科学, 2013, 39(12): 149-152. (Wei Suyun, Ye Ning, Zhu Jian, et al. Collaborative Filtering Recommendation Algorithm Based on Item Clustering and Global Similarity[J]. Computer Science, 2013, 39(12): 149-152.)
[24] Aggarwal C C. On the Effects of Dimensionality Reduction on High Dimensional Similarity Search[C]. In: Proceedings of the 20th ACM Sigmod-Sigact-Sigart Symposium on Principles of Database Systems. 2001: 256-266.Papagelis M, Plexousakis D, Kutsuras T. Alleviating the Sparsity Problem of Collaborative Filtering Using Trust Inferences[C]. In: Proceedings of the 3rd International Conference on Trust Management. Berlin, Heidelberg: Springer-Verlag, 2005: 224-239.

[1]	张怡文,张臣坤,杨安桔,计成睿,岳丽华. 基于条件型游走的四部图推荐方法^*[J]. 数据分析与知识发现, 2019, 3(4): 117-125.
[2]	叶佳鑫,熊回香. 基于标签的跨领域资源个性化推荐研究^*[J]. 数据分析与知识发现, 2019, 3(2): 21-32.
[3]	李杰,杨芳,徐晨曦. 考虑时间动态性和序列模式的个性化推荐算法^*[J]. 数据分析与知识发现, 2018, 2(7): 72-80.
[4]	王道平,蒋中杨,张博卿. 基于灰色关联分析和时间因素的协同过滤算法^*[J]. 数据分析与知识发现, 2018, 2(6): 102-109.
[5]	王永,王永东,郭慧芳,周玉敏. 一种基于离散增量的项目相似性度量方法^*[J]. 数据分析与知识发现, 2018, 2(5): 70-76.
[6]	花凌锋,杨高明,王修君. 面向位置的多样性兴趣新闻推荐研究^*[J]. 数据分析与知识发现, 2018, 2(5): 94-104.
[7]	侯君,刘魁,李千目. 基于ESSVM的分类推荐^*[J]. 数据分析与知识发现, 2018, 2(3): 9-21.
[8]	涂海丽,唐晓波. 基于标签的商品推荐模型研究^*[J]. 数据分析与知识发现, 2017, 1(9): 28-39.
[9]	侯银秀,李伟卿,王伟军,张婷婷. 基于用户偏好与商品属性情感匹配的图书个性化推荐研究^*[J]. 数据分析与知识发现, 2017, 1(8): 9-17.
[10]	薛福亮,刘君玲. 基于用户间信任关系改进的协同过滤推荐方法^*[J]. 数据分析与知识发现, 2017, 1(7): 90-99.
[11]	覃幸新,王荣波,黄孝喜,谌志群. 基于多权值的Slope One协同过滤算法^*[J]. 数据分析与知识发现, 2017, 1(6): 65-71.
[12]	陈梅梅,薛康杰. 基于标签簇多构面信任关系的个性化推荐算法研究^*[J]. 数据分析与知识发现, 2017, 1(5): 94-101.
[13]	陈梅梅, 薛康杰. 基于改进张量分解模型的个性化推荐算法研究^*[J]. 数据分析与知识发现, 2017, 1(3): 38-45.
[14]	李道国,李连杰,申恩平. 基于用户评分时间改进的协同过滤推荐算法^*[J]. 现代图书情报技术, 2016, 32(9): 65-69.
[15]	谭学清,张磊,黄翠翠,罗琳. 融合领域专家信任与相似度的协同过滤推荐算法研究^*[J]. 现代图书情报技术, 2016, 32(7-8): 101-109.

Viewed

Full text

Abstract

Cited

Shared

Discussed