计算机科学 ›› 2018, Vol. 45 ›› Issue (5): 108-115.doi: 10.11896/j.issn.1002-137X.2018.05.019

• 信息安全 • 上一篇    下一篇

基于多重信任的协同过滤推荐算法

于阳,于洪涛,黄瑞阳   

  1. 国家数字交换系统工程技术研究中心 郑州450002,国家数字交换系统工程技术研究中心 郑州450002,国家数字交换系统工程技术研究中心 郑州450002
  • 出版日期:2018-05-15 发布日期:2018-07-25
  • 基金资助:
    本文受国家自然科学基金创新群体项目(61521003),国家自然科学基金资助

Collaborative Filtering Recommendation Algorithm Based on Multiple Trust

YU Yang, YU Hong-tao and HUANG Rui-yang   

  • Online:2018-05-15 Published:2018-07-25

摘要: 针对评分数据稀疏性和用户冷启动所导致的协同过滤推荐系统的准确度与覆盖率较低的问题,文中融合显性信任和隐性信任因素,提出了一种基于多重信任的协同过滤推荐算法。首先,依据用户间推荐评分的准确性与可依赖度因子,提出一种改进的均方差(Mean Squared Difference,MSD)信任度量方法,并在此基础上提出基于隐性信任信息的评分模型;其次,以最大信任传播距离为约束,提出一种显性信任信息的关系模型;最后,依据评分相似性与显性信任关系,利用0-1背包组合优化策略选择出目标用户的最优近邻集合,从而进行评分预测。在Epinions数据集上与多种主流算法的对比仿真实验结果表明,该算法通过引入有效评分和显性信任关系,极大地缓解了数据稀疏性和冷启动问题,并且在不牺牲覆盖率的条件下显著提升了推荐准确度。

关键词: 协同过滤,稀疏性,冷启动,显性信任,隐性信任,0-1背包问题

Abstract: Aiming at the reduction of accuracy and coverage for collaborative filtering recommendation system caused by sparseness of scoring data and cold start of users,this paper integratesd the explicit trust and implicit trust factors,and proposed a collaborative filtering recommendation algorithm based on multiple trust.Firstly,an improved Mean Squared Difference(MSD) trust metric method was proposed based on the accuracy and dependability factor of the recommended scores among users.Based on this,a scoring model based on implicit trust information was proposed.Secondly,regar-ding the maximum trust propagation distance as the constraint,a relational model of explicit trust information was proposed.Finally,based on the similarity between the score and the explicit trust,the optimal neighbor set of the target user was selected by the 0-1backpack combination optimization strategy,and the scoring prediction was carried out.Comparisons of the simulation results with a variety of state-of-the-art algorithms on Epinions dataset demonstrate that the proposed algorithm can greatly alleviate the data sparsity and cold start problems by introducing effective score and explicit trust relationship,and significantly improve the recommendation accuracy while preserving good coverage.

Key words: Collaborative filtering,Sparsity,Cold start,Explicit trust,Iimplicit trust,0-1 knapsack problem

[1] JANNACH D,ZANKER M,FELFERNIG A,et al.推荐系统[M].北京:人民邮电出版社,2013.
[2] AGGARWAL C C.Neighborhood-Based Collaborative Filtering[M]∥Recommender Systems.Springer International Publi-shing,2016:29-70.
[3] YU Y,YU H T,HUANG R Y.Collaborative filtering recommendation algorithm based on entropy optimization nearest-neighbor selection[J].Application Research of Computers,2017,34(9):2618-2623.(in Chinese) 于阳,于洪涛,黄瑞阳.基于熵优化近邻选择的协同过滤推荐算法[J].计算机应用研究,2017,34(9):2618-2623.
[4] DONG Y,ZHAO C,CHENG W,et al.A Personalized Recommendation Algorithm with User Trust in Social Network[C]∥International Conference of Young Computer Scientists,Engineers and Educators.Singapore:Springer,2016:63-76.
[5] FERNNDEZ-TOBAS I,BRAUNHOFER M,ELAHI M,etal.Alleviating the new user problem in collaborative filtering by exploiting personality information[J].User Modeling and User-Adapted Interaction,2016,6(2/3):221-255.
[6] PEREIRA A L V,HRUSCHKA E R.Simultaneous co-cluste-ring and learning to address the cold start problem in recommender systems[J].Knowledge-Based Systems,2015,82(C):11-19.
[7] JIE Q,LEI C,HUI P.A solution of missing value in collaborative filtering recommendation algorithm[C]∥Chinese Automation Congress(CAC),2015.IEEE,2015:2184-2187.
[8] CHOI K,SUH Y,YOO D.Extended Collaborative FilteringTechnique for Mitigating the SparsityProblem[J].International Journal of Computers,Communications & Control,2016,11(5):631.
[9] OCEPEK U,RUGELJ J,BOSNIˇ Z.Improving matrix factorization recommendations for examples in cold start[J].Expert Systems with Applications,2015,42(19):6784-6794.
[10] ZHANG J,Lin Y,LIN M,et al.An effective collaborative filtering algorithm based on user preference clustering[J].Applied Intelligence,2016,45(2):230-240.
[11] KONSTAS I,STATHOPOULOS V,JOSE J M.On social networks and collaborative recommendation[C]∥32nd Internatio-nal ACM SIGIR Conference on Research and Development in Information Retrieval.ACM,2009:195-202.
[12] PARK C,KIM D,OH J,et al.Improving top-K recommendation with truster and trustee relationship in user trust network[J].Information Sciences,2016,374(C):100-114.
[13] SINGLA P,RICHARDSON M.Yes,there is a correlation:-from social networks to personal behavior on the web[C]∥17th International Conference on World Wide Web.ACM,2008:655-664.
[14] SUN Z,HAN L,HUANG W,et al.Recommender systemsbased on social networks[J].Journal of Systems and Software,2015,99(C):109-119.
[15] GAO P,MIAO H,BARAS J S,et al.Star:semiring trust infe-rence for trust-aware social recommenders[C]∥10th ACM Conference on Recommender Systems.ACM,2016:301-308.
[16] GUO G.Integrating trust and similarity to ameliorate the data sparsity and cold start for recommender systems[C]∥7th ACM Conference on Recommender Systems.ACM,2013:451-454.
[17] GUO G,ZHANG J,THALMANN D,et al.From ratings totrust:an empirical study of implicit trust in recommender systems[C]∥Proceedings of the 29th Annual ACM Symposium on Applied Computing.ACM,2014:248-253.
[18] PAPAGELIS M,PLEXOUSAKIS D,KUTSURAS T.Alleviating the sparsity problem of collaborative filtering using trust inferences[C]∥International Conference on Trust Management.Berlin:Springer,2005:224-239.
[19] O’DONOVAN J,SMYTH B.Trust in recommender systems[C]∥10th International Conference on Intelligent User Interfaces.ACM,2005:167-174.
[20] HWANG C S,CHEN Y P.Using trust in collaborative filtering recommendation[C]∥International Conference on Industrial,Engineering and Other Applications of Applied Intelligent Systems.Berlin:Springer,2007:1052-1060.
[21] SHAMBOUR Q,LU J.A trust-semantic fusion-based recom-mendation approach for e-business applications[J].Decision Support Systems,2012,54(1):768-780.
[22] BEDI P,SHARMA R.Trust based recommender system using ant colony for trust computation[J].Expert Systems with Applications,2012,39(1):1183-1190.
[23] TANG J,HU X,GAO H,et al.Exploiting Local and Global Social Context for Recommendation[C]∥IJCAI.2013:264-269.
[24] GOLBECK J A.Computing and applying trust in web-based social networks[M].University of Maryland at College Park,2005.
[25] MASSA P,AVESANI P.Trust-aware recommender systems[C]∥2007 ACM Conference on Recommender Systems.ACM,2007:17-24.
[26] CHOWDHURY M,THOMO A,WADGE W W.Trust-BasedInfinitesimals for Enhanced Collaborative Filtering[C]∥COMAD.2009.
[27] RAY S,MAHANTI A.Improving prediction accuracy in trusta-ware recommender systems[C]∥2010 43rd Hawaii Internatio-nal Conference on System Sciences(HICSS).IEEE,2010:1-9.
[28] GUO G,ZHANG J,THALMANN D.Merging trust in collaborative filtering to alleviate data sparsity and cold start[J].Knowledge-Based Systems,2014,57(2):57-68.
[29] MORADI P,AHMADIAN S.A reliability-based recommenda-tion method to improve trust-aware recommender systems[J].Expert Systems with Applications,2015,42(21):7386-7398.
[30] HERNANDO A,BOBADILLA J S,ORTEGA F,et al.Incorporating reliability measurements into the predictions of a recommender system[J].Information Sciences,2013,218(218):1-16.
[31] YUAN W,GUAN D,LEE Y K,et al.The small-world trust network[J].Applied Intelligence,2011,35(3):399-410.
[32] ZHU Y X,LV L Y.Evaluation Metrics for Recommender Systems[J].Journal of University of Electronics Science and Technology of China,2012,1(2):163-175.(in Chinese) 朱郁筱,吕琳媛.推荐系统评价指标综述[J].电子科技大学学报,2012,41(2):163-175.

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!