Please wait a minute...
Advanced Search
数据分析与知识发现  2017, Vol. 1 Issue (7): 90-99     https://doi.org/10.11925/infotech.2096-3467.2017.07.11
  首届"数据分析与知识发现"学术研讨会专辑(I) 本期目录 | 过刊浏览 | 高级检索 |
基于用户间信任关系改进的协同过滤推荐方法*
薛福亮(), 刘君玲
天津财经大学商学院 天津 300222
Improving Collaborative Filtering Recommendation Based on Trust Relationship Among Users
Xue Fuliang(), Liu Junling
Business School, Tianjin University of Finance & Economics, Tianjin 300222, China
全文: PDF (614 KB)   HTML ( 1
输出: BibTeX | EndNote (RIS)      
摘要 

目的】利用用户间信任关系改进协同过滤推荐中用户相似性计算精度, 即在目标用户没有相似用户的前提下, 从其信任用户中选择信任值高的作为相似用户, 进而提高相似用户聚类效果, 提高推荐质量, 并有效缓解协同过滤推荐稀疏性和冷启动问题。【方法】筛选信任用户作为相似用户; 根据选择的信任用户和目标用户形成一个项目的评分集, 并对目标用户未评价过的项目进行评分估算(根据信任用户评分进行简单的评分计算); 将用户间的信任关系依据方差大小进行量化, 形成一个调节因子。本文的创新点就在于调节因子的计算, 并将调节因子纳入用户相似性计算, 形成相似性用户聚类簇, 在此基础上在相似用户之间进行交叉推荐。【结果】通过平均绝对误差指标进行实验评价, 结果表明基于信任关系的协同过滤推荐方法相比传统协同过滤, 在推荐精度上更加准确, 并同时有效缓解了冷启动和稀疏性问题。【局限】本文提出的方法仅在具有信任关系的一个算例上进行实验测试, 需在其他数据集和真实应用场景下进一步检验。【结论】用户间信任关系蕴涵非常有价值的信息, 对用户信任关系进行量化, 并纳入用户相似性计算, 在此基础上实施协同过滤推荐, 对缓解冷启动与稀疏性问题具有较好的理论和实践意义。

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
薛福亮
刘君玲
关键词 电子商务推荐用户信任协同过滤冷启动稀疏性    
Abstract

[Objective] This paper tries to improve user similarity calculation in collaborative filtering recommendation with trust relationship among them. Once there is no similar user for members of the target group, we recommend the most trusted ones as the similar users. [Methods] First, we retrieved the trusted users as candidates for the similar users. Second, we combined the trusted and the target users to form a project score set, and evaluated the estimated value of the projects receiving no comment from the target group. Third, we quantified the trust relationship among users to form a regulation factor. Finally, we calculated the adjustment factor and created the similarity cluster of users, and made cross-recommendation among similar users. [Results] The collaborative filtering recommendation method based on trust relationship had better performance than traditional ones. [Limitations] Only examined the new method with one sample dataset with trusted relationship. More research is needed to test the proposed method with other datasets. [Conclusions] The trusted relationship among users contains valuable information, which could be used to calculate user similarity for collaborative filtering recommendation services, and then effectively solves the sparsity and cold start issue.

Key wordsE-commerce Recommendation    User Trust    Collaborative Filtering    Cold Start    Sparsity
收稿日期: 2017-05-26      出版日期: 2017-09-13
ZTFLH:  TP301.6  
基金资助:*本文系教育部人文社会科学一般项目“电子商务环境下顾客购物偏好推荐及企业利润挖掘”(项目编号: 13YJC630195)的研究成果之一
引用本文:   
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.
Xue Fuliang,Liu Junling. Improving Collaborative Filtering Recommendation Based on Trust Relationship Among Users. Data Analysis and Knowledge Discovery, 2017, 1(7): 90-99.
链接本文:  
https://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/10.11925/infotech.2096-3467.2017.07.11      或      https://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/Y2017/V1/I7/90
  引入用户信任关系后的协同推荐核心框架
i1 i2 i3 i4 i5 i6 i7 i8 i9
u1 5
u2 5 4 3 2
u3 4 3 1
u4 3 5 2
u5 4 4 3 3
u6 3 3 5 5
u7 5 4
u8 4 2 1
u9 4 5 5
  用户对项目的评分
u1 u2 u3 u4 u5 u6 u7 u8 u9
u1 1 1
u2 1 1
u3 1 1
u4 1
u5 1 1
u6 1 1
u7
u8
u9
  用户与用户之间的信任关系
u1 u2 u3 u4 u5 u6 u7 u8 u9
d 0 1 1 2 3 4
tu1, uk 1.00 1.00 1.00 0.50 0.33 0.25
  u1和信任网络中的信任用户的信任值
i1 i2 i3 i4 i5 i6 i7 i8 i9
4.33 4 5 3 2.73 1.71
0.29 1.00 1.00 0.29 0.81 0.67
  合并后的u1的评分
u1 u2 u3 u4 u5 u6 u7 u8 u9
S 1.0 0.870 0.992 0.910 0.910 -0.910 1.0 -0.950
S 1.0 0.660 0.995 0.980 0.840 -0.780 0.990 -0.980
S 1.0 0.699 0.955 0.985 0.910 -0.828 0.982 -0.968
  u1和信任用户的相似值
指标 CF CCF ECF
iMAE 0.9985 0.9986 0.9987
F1 0.7994 0.7995 0.7996
  算例上的预测性能表
[1] Wang Y, Singh M P.Formal Trust Model for Multiagent System[C]//Proceedings of the 20th International Joint Conference on Artificial Intelligence.2007: 1551-1556.
[2] Lampropoulos A S, Lampropoulos P S, Tsihrintzis G A.A Cascade-Hybrid Music Recommender System for Mobile Services Based on Musical Genre Classification and Personality Diagnosis[J]. Multimedia Tools and Applications, 2012, 59(1): 241-258.
doi: 10.1007/s11042-011-0742-0
[3] Shambour Q, Lu J.A Trust-semantic Fusion-based Recommendation Approach for E-business Application[J]. Decision Support Systems, 2012, 54(1): 768-780.
doi: 10.1016/j.dss.2012.09.005
[4] Adomavicius G, Tuzhilin A.Toward the Next Generation of Recommender Systems: A Survey of the State-of-the-art and Possible Extensions[J]. IEEE Transactions on Knowledge and Data Engineering, 2005, 17(6): 734-749.
doi: 10.1109/TKDE.2005.99
[5] Jøsang A, Quattrociocchi W, Karabeg D.Taste and Trust[C]//Proceedings of IFIP International Conference on Trust Management.2011: 312-322.
[6] Chowdhury M, Thomo A, Wadge W W.Trust-based Infinitesimals for Enhanced Collaborative Filtering[C]// Proceedings of the 15th International Conference on Management of Data. 2009.
[7] Danis C, Singer D.A Wiki Instance in the Enterprise: Opportunities, Concerns and Reality[C]//Proceedings of the 2008 ACM Conference on Computer Supported Cooperative Work.2008: 495-504.
[8] De Rosa C, Cantrell J, Havens A, et al.Sharing, Privacy and Trust in Our Networked World[R]. A Report to the OCLC Membership, OCLC, 2007.
[9] Golbeck J A.Computing and Applying Trust in Web-Based Social Networks[D]. College Park, MD, USA: University of Maryland at College Park, 2005.
[10] 余力, 刘鲁. 电子商务个性化推荐研究[J]. 计算机集成制造系统, 2004, 10(10): 1306-1313.
doi: 10.3969/j.issn.1006-5911.2004.10.025
[10] (Yu Li, Liu Lu.Research on Personalized Recommendations in E-business[J]. Computer Integrated Manufacturing Systems, 2004, 10(10): 1306-1313.)
doi: 10.3969/j.issn.1006-5911.2004.10.025
[11] 刘建国, 周涛, 汪秉宏. 个性化推荐系统的研究进展[J]. 自然科学进展, 2009, 19(1): 1-15.
doi: 10.3321/j.issn:1002-008X.2009.01.001
[11] (Liu Jianguo, Zhou Tao, Wang Binghong.Study on the Research of Personalized Recommendation System[J]. Progress in Natural Science, 2009, 19(1): 1-15.)
doi: 10.3321/j.issn:1002-008X.2009.01.001
[12] 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.
[12] (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.)
[13] 龙宇, 童向荣. 结合信任的推荐系统的性质[J]. 计算机应用, 2014, 34(1): 222-226, 235.
doi: 10.11772/j.issn.1001-9081.2014.01.0222
[13] (Long Yu, Tong Xiangrong.Property of Trust-based Recommendation System[J]. Journal of Computer Applications, 2014, 34(1): 222-226, 235.)
doi: 10.11772/j.issn.1001-9081.2014.01.0222
[14] 邹本友, 李翠平, 谭力文, 等. 基于用户信任和张量分解的社会网络推荐[J]. 软件学报, 2014, 25(12): 2852-2864.
doi: 10.13328/j.cnki.jos.004725
[14] (Zou Benyou, Li Cuiping, Tan Liwen, et al.Social Recommendations Based on User Trust and Tensor Factorization[J]. Journal of Software, 2014, 25(12): 2852-2864.)
doi: 10.13328/j.cnki.jos.004725
[15] Guo G, Zhang J, Thalmann D.Merging Trust in Collaborative Filtering to Alleviate Data Sparsity and Cold Start[J]. Knowledge-Based Systems, 2014, 57: 57-68.
doi: 10.1016/j.knosys.2013.12.007
[16] Ma X, Lu H, Gan Z, et al.An Explicit Trust and Distrust Clustering Based Collaborative Filtering Recommendation Approach[J]. Electronic Commerce Research and Applications, 2017, 25: 29-39.
doi: 10.1016/j.elerap.2017.06.005
[17] Jia D, Zhang F, Liu S.A Robust Collaborative Filtering Recommendation Algorithm Based on Multidimensional Trust Model[J]. Journal of Software, 2013, 8(1): 11-18.
doi: 10.4304/jsw.8.1.11-18
[18] Xu X L, Xu G L.Improved Collaborative Filtering Recommendation Based on Classification and User Trust[J]. Journal of Electronic Science and Technology, 2016, 14(1): 25-31.
doi: 10.11989/JEST.1674-862X.504071
[19] Du Y, Du X, Huang L.Improve the Collaborative Filtering Recommender System Performance by Trust Network Construction[J]. Chinese Journal of Electronics, 2016, 25(3): 418-423.
doi: 10.1049/cje.2016.05.005
[20] Jamali M, Ester M.Trustwalker: A Random Walk Model for Combining Trust-based and Item-based Recommendation[C]// Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2009: 397-406.
[21] Diaz-Aviles E, Drumond L, Schmidt-Thieme L, et al.Real-time Top-n Recommendation in Social Streams[C]// Proceedings of the 6th ACM Conference on Recommender Systems.2012: 59-66.
[22] 陈宇亮, 沈奎林. 基于读者评论的图书推荐系统研究[J]. 图书情报导刊, 2016, 1(9): 6-9.
[22] (Chen Yuliang, Shen Kuilin.Study on Book Recommendation System Based on Reader’s Comments[J]. Journal of Library and Information Science, 2016, 1(9): 6-9.)
[23] 李琦. 基于社交网络好友信任度的个性化推荐系统研究[D]. 哈尔滨: 哈尔滨工业大学, 2014.
[23] (Li Qi.Study on Personalized Recommendation System Based on Social Network Friends’ Trust [D]. Harbin: Harbin Institute of Technology, 2014.)
[24] 肖志宇. 基于社交网络和信任模型的推荐系统的研究与实现[D]. 南京: 东南大学, 2015.
[24] (Xiao Zhiyu.Research and Implementation of Recommendation System Based on Social Network and Trust Model [D]. Nanjing: Southeast University, 2015.)
[25] 孙国豪. 社交网络中基于信任的推荐系统[D]. 苏州: 苏州大学, 2015.
[25] (Sun Guohao.Trust-based Recommendation System in Social Network [D]. Suzhou: Soochow University, 2015.)
[26] 朱岩, 林泽楠. 电子商务中的个性化推荐方法评述[J]. 中国软科学, 2009(2): 183-192.
doi: 10.3969/j.issn.1002-9753.2009.02.022
[26] (Zhu Yan, Lin Zenan.A Review of E-Business Recommendation System[J]. Chinese Soft Science, 2009(2): 183-192.)
doi: 10.3969/j.issn.1002-9753.2009.02.022
[27] 李聪, 梁昌勇, 董珂. 基于项目类别相似性的协同过滤推荐算法[J]. 合肥工业大学学报: 自然科学版, 2008, 31(3): 360-363.
[27] (Li Cong, Liang Changyong, Dong Ke.A Collaborative Filtering Recommendation Algorithm Based on Item Category Similarity[J]. Journal of Hefei University of Technology: Natural Science Edition, 2008, 31(3): 360-363.)
[28] 李晓昀, 阳小华, 余颖. 基于隐性反馈分析的个性化推荐研究[J]. 计算机工程与设计, 2009, 30(16): 3794-3796, 3825.
[28] (Li Xiaoyun, Yang Xiaohua, Yu Ying.Research on Individualized Recommendation Based on Implicit Feedback Analyses[J]. Computer Engineering and Design, 2009, 30(16): 3794-3796, 3825.)
[29] 余力, 刘鲁, 李雪峰. 用户多兴趣下的个性化推荐算法研究[J]. 计算机集成制造系统, 2004, 10(12): 1610-1615.
doi: 10.3969/j.issn.1006-5911.2004.12.026
[29] (Yu Li, Liu Lu, Li Xuefeng.Research on Personalized Recommendation Algorithm for Users Multiple-interests[J]. Computer Integrated Manufacturing Systems, 2004, 10(12): 1610-1615.)
doi: 10.3969/j.issn.1006-5911.2004.12.026
[30] 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.
[30] (Sun Xiaohua.Study on Sparsity and Cold Start of Collaborative Filtering System [D]. Hangzhou: Zhejiang University, 2005.)
[31] 许海玲, 吴潇, 李晓东, 等. 互联网推荐系统比较研究[J]. 软件学报, 2009, 20(2): 350-362.
doi: 10.3724/SP.J.1001.2009.03388
[31] (Xu Hailing, Wu Xiao, Li Xiaodong, et al.Comparison Study of Internet Recommendation System[J]. Journal of Software, 2009, 20(2): 350-362.)
doi: 10.3724/SP.J.1001.2009.03388
[1] 冯勇,刘洋,徐红艳,王嵘冰,张永刚. 融合近邻评论的GRU商品推荐模型*[J]. 数据分析与知识发现, 2021, 5(3): 78-87.
[2] 李振宇, 李树青. 嵌入隐式相似群的深度协同过滤算法*[J]. 数据分析与知识发现, 2021, 5(11): 124-134.
[3] 杨辰, 陈晓虹, 王楚涵, 刘婷婷. 基于用户细粒度属性偏好聚类的推荐策略*[J]. 数据分析与知识发现, 2021, 5(10): 94-102.
[4] 杨恒,王思丽,祝忠明,刘巍,王楠. 基于并行协同过滤算法的领域知识推荐模型研究*[J]. 数据分析与知识发现, 2020, 4(6): 15-21.
[5] 苏庆,陈思兆,吴伟民,李小妹,黄佃宽. 基于学习情况协同过滤算法的个性化学习推荐模型研究*[J]. 数据分析与知识发现, 2020, 4(5): 105-117.
[6] 郑淞尹,谈国新,史中超. 基于分段用户群与时间上下文的旅游景点推荐模型研究*[J]. 数据分析与知识发现, 2020, 4(5): 92-104.
[7] 丁勇,陈夕,蒋翠清,王钊. 一种融合网络表示学习与XGBoost的评分预测模型*[J]. 数据分析与知识发现, 2020, 4(11): 52-62.
[8] 焦富森,李树青. 基于物品质量和用户评分修正的协同过滤推荐算法 *[J]. 数据分析与知识发现, 2019, 3(8): 62-67.
[9] 李珊,姚叶慧,厉浩,刘洁,嘎玛白姆. 基于ISA联合聚类的组推荐算法研究 *[J]. 数据分析与知识发现, 2019, 3(8): 77-87.
[10] 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.
[11] 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.
[12] 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.
[13] 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.
[14] 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.
[15] 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.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
版权所有 © 2015 《数据分析与知识发现》编辑部
地址:北京市海淀区中关村北四环西路33号 邮编:100190
电话/传真:(010)82626611-6626,82624938
E-mail:jishu@mail.las.ac.cn