[1]张 莉,孙晓寒,郑晓晗.基于评分子空间和信任机制的协同过滤推荐算法[J].南京师范大学学报(工程技术版),2023,23(03):027-35.[doi:10.3969/j.issn.1672-1292.2023.03.004]
　Zhang Li,Sun Xiaohan,Zheng Xiaohan.Collaborative Filtering Method Based on User Rating Subspace and Trust Mechanism for Recommendation System[J].Journal of Nanjing Normal University(Engineering and Technology),2023,23(03):027-35.[doi:10.3969/j.issn.1672-1292.2023.03.004]
点击复制

基于评分子空间和信任机制的协同过滤推荐算法
分享到：

南京师范大学学报（工程技术版）[ISSN:1006-6977/CN:61-1281/TN]

卷:
23卷
期数:
2023年03期
页码:
027-35
栏目:
计算机科学与技术
出版日期:
2023-09-15

文章信息/Info

Title:
Collaborative Filtering Method Based on User Rating Subspace and Trust Mechanism for Recommendation System
文章编号:
1672-1292(2023)03-0027-09
作者:
张 莉; 孙晓寒; 郑晓晗
(苏州大学计算机科学与技术学院,江苏 苏州 215006)
Author(s):
Zhang Li; Sun Xiaohan; Zheng Xiaohan
(School of Computer Science and Technology, Soochow University, Suzhou 215006, China)
关键词:
推荐系统; 协同过滤; 信任机制; 用户评分子空间; 迭代评分预测
Keywords:
recommendation system;  collaborative filtering;  trust mechanism;  user rating subspaces;  iterative rating prediction
分类号:
TP391
DOI:
10.3969/j.issn.1672-1292.2023.03.004
文献标志码:
A
摘要:
互联网技术的快速发展导致了互联网上数据信息的爆炸式增长. 推荐系统作为解决互联网信息过载问题的关键技术,其核心思想是通过用户历史行为数据挖掘出用户的个性化偏好,为用户推荐其感兴趣的物品. 然而,稀疏的评分数据会导致相似度计算不够准确,进而影响相似用户集的质量. 为了提高相似用户搜索的可靠性,引入信任机制和评分子空间,提出基于评分子空间和信任机制的协同过滤推荐算法. 创新点主要包括以下两点:首先,算法引入基于用户显式声明的关系数据所构建的信任机制,该关系数据能够对稀疏的评分数据进行补充. 其次,利用评分子空间和信任关系,设计了一种基于隐式和显式相似度的混合相似度度量方式,并将之引入到多阶近邻的相似用户搜索方法和迭代评分预测方案中. 实验结果表明,所提算法提高了推荐的准确度,具备较好的预测能力.
Abstract:
The rapid growth of the internet has led to the explosive growth of information on the internet. To solve the issue of information overload, recommendation system has been proposed. The core idea behind recommendation system is to explore users' personalized preferences based on users' historical behavior data, and recommend items that match users' interests to users. However, sparse rating data leads to poor accurate similarity calculations, which in turn affect the quality of similar user sets. To improve the reliability of similar user set, this paper proposes a collaborative filtering algorithm based on user rating subspace and trust mechanism(URSTM)for recommendation system. The innovation of this paper contains the following two main points. Firstly, URSTM introduces a trust mechanism constructed based on a trust relationship explicitly declared by users, which can supplement the sparse rating data. Secondly, by using the rating subspace and trust relationship, this paper designs a hybrid similarity measurement based on explicit and implicit similarities, and then integrates it into the multi-order nearest neighbor search method and iterative rating prediction method. Experimental results show that URSTM can improve the accuracy of recommendation performance and has a better prediction ability.

参考文献/References:

[1]GOLDBERG D,NICHOLS D,OKI B M,et al. Using collaborative filtering to weave an information tapestry[J]. Communications of the ACM,1992,35(12):61-70.
[2]RESNICK P,VARIAN H R. Recommender systems[J]. Communications of the ACM,1997,40(3):56-58.
[3]LE Q H,VU S L,LE T X. A state-of-the-art survey on context-aware recommender systems and applications[J]. International Journal of Knowledge and Systems Science,2021,12(3):1-20.
[4]HE C,PARRA D,VERBERT K. Interactive recommender systems:A survey of the state of the art and future research challenges and opportunities[J]. Expert Systems with Applications,2016,56:9-27.
[5]CEN Y K,ZHANG J W,ZOU X,et al. Controllable multi-interest framework for recommendation[C]//The 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. New York,NY,USA,2020.
[6]TOLLON F. Designed to seduce:epistemically retrograde ideation and youtube's recommender system[J]. International Journal of Technoethics,2021,12(2):60-71.
[7]MEDEL D,GONZÁLEZ-GONZÁLEZ C S,ACIAR S V. Social relations and methods in recommender systems:A systematic review[J]. International Journal of Interactive Multimedia and Artificial Intelligence,2022,7(4):7.
[8]DU C,GAO Z,YUAN S,et al. Exploration in online advertising systems with deep uncertainty-aware learning[C]//Proceedings of the 27th ACM SIGKDD Conference Discovery and Data Mining. New York,NY,USA,2021.
[9]ZANGERLE E,BAUER C. Evaluating recommender systems:survey and framework[J]. ACM Computing Surveys,2023,55(8):1-38.
[10]HERLOCKER J L,KONSTAN J A,BORCHERS A,et al. An algorithmic framework for performing collaborative filtering[J]. ACM SIGIR Forum,2017,51(2):227-234.
[11]AFSAR M M,CRUMP T,FAR B H. Reinforcement learning based recommender systems:a survey[J]. ACM Computing Surveys,2023,55(7):1-38.
[12]JIN R M,LI D,GAO J,et al. Towards a better understanding of linear models for recommendation[C]//Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. New York,NY,USA:Association for Computing Mechinery,2021.
[13]ZHANG Z,ZHANG Y,REN Y. Employing neighborhood reduction for alleviating sparsity and cold start problems in user-based collaborative filtering[J]. Information Retrieval Journal,2020,23:449-72.
[14]WANG R,JIANG Y,LOU J. Attention-based dynamic user preference modeling and nonlinear feature interaction learning for collaborative filtering recommendation[J]. Applied Soft Computing,2021,110:107652.
[15]RAMEZANI M,TAB F A,ABDOLLAHPOURI A,et al. A new generalized collaborative filtering approach on sparse data by extracting high confidence relations between users[J]. Information Sciences,2021,570:323-41.
[16]PAPADAKIS H,PAPAGRIGORIOU A,PANAGIOTAKIS C,et al. Collaborative filtering recommender systems taxonomy[J]. Knowledge and Information Systems,2022,64(1):35-74.
[17]SUN H,PENG Y,CHEN J,et al. A new similarity measure based on adjusted euclidean distance for memory-based collaborative filtering[J]. J Softw,2011,6(6):993-1000.
[18]KHOJAMLI H,RAZMARA J. Survey of similarity functions on neighborhood-based collaborative filtering[J]. Expert Systems with Applications,2021,185:115482.
[19]BAG S,KUMAR S K,TIWARI M K. An efficient recommendation generation using relevant Jaccard similarity[J]. Information Sciences,2019,483:53-64.
[20]MARGARIS D,VASSILAKIS C. Improving collaborative filtering's rating prediction coverage in sparse datasets by exploiting the ‘friend of a friend'concept[J]. International Journal of Big Data Intelligence,2020,7(1):47-57.
[21]SUN X,ZHANG L. Multi-order nearest neighbor prediction for recommendation systems[J]. Digital Signal Processing,2022,127:103540.
[22]RAMEZANI M,MORADI P,AKHLAGHIAN F. A pattern mining approach to enhance the accuracy of collaborative filtering in sparse data domains[J]. Physica a Statistical Mechanics & Its Applications,2014,408:72-84.
[23]KOOHI H,KIANI K. A new method to find neighbor users that improves the performance of collaborative filtering[J]. Expert Systems with Applications,2017,83:30-39.
[24]孙晓寒,张莉. 基于评分区域子空间的协同过滤推荐算法[J]. 计算机科学,2022,49(7):50-56.
[25]MORADI P,AHMADIAN S. A reliability-based recommendation method to improve trust-aware recommender systems[J]. Expert Systems with Applications,2015,42(21):7386-98.
[26]GUO G,ZHANG J,YORKE-SMITH N. A Novel Evidence-Based Bayesian Similarity Measure for Recommender Systems[J]. ACM Transactions on the Web,2016,10(2):1-30.
[27]GUO G,ZHANG J,THALMANN D,et al. ETAF:An extended trust antecedents framework for trust prediction[C]//2014 IEEE Interational Conference on Advances in Social Networks Analysis and Mining. Beijing,China:IEEE,2014.
[28]MASSA P,SOUREN K,SALVETTI M,et al. Trustlet,Open Research on Trust Metrics[J]. Scalable Computing Practice Experience,2008,9(4):31-44.
[29]SALEEM F,ILTAF N,AFZAL H,et al. Using trust in collaborative filtering for recommendations[C]//IEEE 28th International Conference on Enabling Technologies:Infrastructure for Collaborative Enterprises. Kyoto,Japan,2007.
[30]RAHIM A,DURRANI M Y,GILLANI S A,et al. An efficient recommender system algorithm using trust data[J]. The Journal of Supercomputing,2022,78(3):3184-204.
[31]YUAN W W,GUAN D H,LEE Y K,et al. The small-world trust network[J]. Applied Intelligence,2011,35(3):399-410.

相似文献/References:

[1]李 慧,李存华,王 霞.一种新颖的个性化视频搜索排名算法[J].南京师范大学学报(工程技术版),2008,08(04):182.
　L iH u,i L iCunhua,W ang X ia.A Novel Individualized V ideo Search Rank ing Algorithm[J].Journal of Nanjing Normal University(Engineering and Technology),2008,08(03):182.
[2]贺 宇,史有群,陶 然,等.基于服装图像视觉特征的冷启动问题缓解[J].南京师范大学学报(工程技术版),2019,19(03):015.[doi:10.3969/j.issn.1672-1292.2019.03.003]
　He Yu,Shi Youqun,Tao Ran,et al.Mitigation of Cold-Start Problem Based on Visual Features of Clothing Images[J].Journal of Nanjing Normal University(Engineering and Technology),2019,19(03):015.[doi:10.3969/j.issn.1672-1292.2019.03.003]
[3]吴佳炜,沈玲玲,钱 钢.融合项目聚类和时间权重的动态协同过滤算法[J].南京师范大学学报(工程技术版),2017,17(03):063.[doi:10.3969/j.issn.1672-1292.2017.03.010]
　Wu Jiawei,Shen Lingling,Qian Gang.Dynamic Collaborative Filtering Algorithm FusingItem Clustering and Time Weight[J].Journal of Nanjing Normal University(Engineering and Technology),2017,17(03):063.[doi:10.3969/j.issn.1672-1292.2017.03.010]
[4]王俊淑,张国明,胡 斌.基于深度学习的推荐算法研究综述[J].南京师范大学学报(工程技术版),2018,18(04):033.[doi:10.3969/j.issn.1672-1292.2018.04.006]
　Wang Junshu,Zhang Guoming,Hu Bin.A Survey of Deep Learning Based Recommendation Algorithms[J].Journal of Nanjing Normal University(Engineering and Technology),2018,18(03):033.[doi:10.3969/j.issn.1672-1292.2018.04.006]

备注/Memo

备注/Memo:
收稿日期:2023-04-24.
基金项目:江苏省高校自然科学研究项目(19KJA550002)、江苏省六大人才高峰项目(XYDXX-054)、江苏高校优势学科建设工程资助项目.
通讯作者:张莉,博士,教授,研究方向:机器学习,模式识别,神经网络和智能信息处理. E-mail:zhangliml@suda.edu.cn
更新日期/Last Update: 2023-09-15