区块链在个性化推荐系统中的应用研究综述

doi:10.11959/j.issn.2096-0271.2022031

摘要/Abstract

摘要：

区块链作为一种新兴技术，以其去中心化、难以篡改、匿名性和可追溯性等特点，为个性化推荐系统的改进提供了一种崭新的思路。为此，首先对近年来推荐系统面临的主要问题和区块链技术带来的机遇进行归纳总结，然后采用文献分析方法，从时间分布、文献类型、研究问题和评估指标4个层面，对推荐系统中区块链技术的应用研究进行分析和总结。分析结果表明：区块链对于解决推荐系统的数据安全和隐私保护、数据共享、数据可信和推荐透明度问题有重要意义；已有研究主要集中于解决推荐系统中用户的数据安全和隐私保护问题，而在跨平台数据共享、数据激励机制设计和系统可扩展性等方面的研究仍有待进一步突破。

关键词: 区块链, 推荐系统, 隐私安全, 透明可信

Abstract:

Blockchain, as an emerging technology, provides a brand-new idea for the improvement of personalized recommender systems with its characteristics of decentralization, tamper-proof, anonymity and traceability.Therefore, the main problems faced by the recommender systems in recent years and the opportunities brought by blockchain technology were summarized firstly.Then, literature analysis was adopted to analyze and summarize the research on the application of blockchain technology in recommender systems from four aspects: time distribution, literature types, research questions and evaluation indicators.The results show that the blockchain is of great significance for solving the problems of data security and privacy protection, data sharing, data trustworthiness and recommendation transparency of recommender systems.Existing studies mainly focus on solving the problem of data security and privacy protection in recommender systems, while further breakthroughs are needed in cross-platform data sharing, design of incentive mechanisms and system scalability.

Key words: blockchain, recommender systems, privacy and security, transparency and reliability

中图分类号:

许小颖, 陈熙, 陈源, 谢永靖. 区块链在个性化推荐系统中的应用研究综述[J]. 大数据, 2022, 8(3): 87-102.

Xiaoying XU, Xi CHEN, Yuan CHEN, Yongjing XIE. A review of blockchain applications in personalized recommender systems[J]. Big Data Research, 2022, 8(3): 87-102.

图/表 4

图1

图2

表1

表2

参考文献 51

[1]	SCHAFER J B , KONSTAN J A , RIEDL J . E-commerce recommendation applications[J]. Data Mining and Knowledge Discovery, 2001,5(1-2): 115-153.
[2]	JANNACH D , ZANKER M , FELFERNIG A ,et al. Recommender systems:an introduction[M]. Cambridge: Cambridge University Press, 2010.
[3]	SMUTKUPT P , KRAIRIT D , ESICHAIKUL V . Mobile marketing:implications for marketing strategies[J]. International Journal of Mobile Marketing, 2010,5(2): 126-140.
[4]	CHEN P T , HSIEH H P . Personalized mobile advertising:its key attributes,trends,and social impact[J]. Technological Forecasting and Social Change, 2012,79(3): 543-557.
[5]	NAJAFABADI M K , MOHAMED A , ONN C W . An impact of time and item influencer in collaborative filtering recommendations using graph-based model[J]. Information Processing ＆ Management, 2019,56(3): 526-540.
[6]	ADOMAVICIUS G , TUZHILIN A . Toward the next generation of recommender systems:a survey of the state-of-theart and possible extensions[J]. IEEE Transactions on Knowledge and Data Engineering, 2005,17(6): 734-749.
[7]	FAN W Q , MA Y , LI Q ,et al. Graph neural networks for social recommendation[C]// Proceedings of the 19th World Wide Web Conference. New York:ACM Press, 2019: 417-426.
[8]	MAN T , SHEN H W , JIN X L ,et al. Cross-domain recommendation:an embedding and mapping approach[C]// Proceedings of the 26th International Joint Conference on Artificial Intelligence. California:International Joint Conferences on Artificial Intelligence Organization, 2017: 2464-2470.
[9]	VAN DYKE T P , MIDHA V , NEMATI H . The effect of consumer privacy empowerment on trust and privacy concerns in e-commerce[J]. Electronic Markets, 2007,17(1): 68-81.
[10]	FREY R , W?RNER D , ILIC A . Collaborative filtering on the blockchain:a secure recommender system for e-commerce[C]// Proceedings of the 22nd Americas Conference on Information Systems. Atlanta:AIS Electronic Library, 2016: 1-5.
[11]	GENTRY C . A fully homomorphic encryption scheme[D]. Palo Alto:Stanford University, 2009.
[12]	LINDELL Y , PINKAS B . Secure multiparty computation for privacypreserving data mining[J]. Journal of Privacy and Confidentiality, 2009,1(1): 59-98.
[13]	WANG X H , YANG X X , GUO L ,et al. Exploiting social review-enhanced convolutional matrix factorization for social recommendation[J]. IEEE Access, 2019,7: 82826-82837.
[14]	RESHMA R , AMBIKESH G , THILAGAM P S . Alleviating data sparsity and cold start in recommender systems using social behaviour[C]// Proceedings of 2016 International Conference on Recent Trends in Information Technology. Piscataway:IEEE Press, 2016: 1-8.
[15]	KHERN-AM-NUAI W , KANNAN K , GHASEMKHANI H . Extrinsic versus intrinsic rewards for contributing reviews in an online platform[J]. Information Systems Research, 2018,29(4): 871-892.
[16]	刘彦松, 夏琦, 李柱 ,等. 基于区块链的链上数据安全共享体系研究[J]. 大数据, 2020,6(5): 92-105.
	LIU Y S , XIA Q , LI Z ,et al. Research on secure data sharing system based on blockchain[J]. Big Data Research, 2020,6(5): 92-105.
[17]	MOBASHER B , BURKE R , BHAUMIK R ,et al. Toward trustworthy recommender systems[J]. ACM Transactions on Internet Technology, 2007,7(4): 23.
[18]	WILLIAMS C A , MOBASHER B , BURKE R . Defending recommender systems:detection of profile injection attacks[J]. Service Oriented Computing and Applications, 2007,1(3): 157-170.
[19]	TONG C , YIN X , LI J ,et al. A shilling attack detector based on convolutional neural network for collaborative recommender system in social aware network[J]. The Computer Journal, 2018,61(7): 949-958.
[20]	MEHTA B , HOFMANN T . A survey of attack-resistant collaborative filtering algorithms[J]. IEEE Data Engineering Bulletin, 2008,31(2): 14-22.
[21]	YUAN F , YAO L N , BENATALLAH B . Adversarial collaborative neural network for robust recommendation[C]// Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval. New York:ACM Press, 2019: 1065-1068.
[22]	SINHA R , SWEARINGEN K . The role of transparency in recommender systems[C]// Proceedings of 2002 CHI Conference Extended Abstracts on Human Factors in Computing Systems. New York:ACM Press, 2002: 830-831.
[23]	ZYSKIND G , NATHAN O , PENTLAND A S . Decentralizing privacy:using blockchain to protect personal data[C]// Proceedings of 2015 IEEE Security and Privacy Workshops. Piscataway:IEEE Press, 2015: 180-184.
[24]	DENNIS R , OWENSON G . Rep on the roll:a peer to peer reputation system based on a rolling blockchain[J]. International Journal for Digital Society, 2016,7(1): 1123-1134.
[25]	CARBONI D . Feedback based reputation on top of the bitcoin blockchain[J]. arXiv preprint. 2015,arXiv:1502.01504.
[26]	SCHAUB A , BAZIN R , HASAN O ,et al. A trustless privacy-preserving reputation system[C]// Proceedings of IFIP International Conference on ICT Systems Security and Privacy Protection. Cham:Springer International Publishing, 2016: 398-411.
[27]	杜兰, 朱叶, 田越 ,等. 基于Fabric的图书推荐系统的设计与实现[J]. 新型工业化, 2020,10(9): 50-54.
	DU L , ZHU Y , TIAN Y ,et al. Design and implementation of book recommendation system based on Fabric[J]. The Journal of New Industrialization, 2020,10(9): 50-54.
[28]	赵子军, 应作斌, 杨钊 ,等. 结合区块链和车辆社交网络的车队成员推荐[J]. 西安电子科技大学学报, 2020,47(5): 122-129.
	ZHAO Z J , YING Z B , YANG Z ,et al. Recommendation of platoon members by combining the blockchain and vehicular social network[J]. Journal of Xidian University, 2020,47(5): 122-129.
[29]	杨立, 左春, 梁赓 . 基于区块链的保险产品推荐模型[J]. 计算机系统应用, 2019,28(1): 61-68.
	YANG L , ZUO C , LIANG G . Insurance product recommendation model based on blockchain[J]. Computer Systems ＆Applications, 2019,28(1): 61-68.
[30]	LI X L , DU E X , CHEN C ,et al. Blockchain-based credible and privacypreserving QoS-aware web service recommendation[C]// Proceedings of 2019 International Conference on Blockchain and Trustworthy Systems. Singapore:Springer Singapore, 2019: 621-635.
[31]	CASINO F , PATSAKIS C . An efficient blockchain-based privacy-preserving collaborative filtering architecture[J]. IEEE Transactions on Engineering Management, 2020,67(4): 1501-1513.
[32]	BOSRI R , RAHMAN M S , BHUIYAN M Z A ,et al. Integrating blockchain with artificial intelligence for privacypreserving recommender systems[J]. IEEE Transactions on Network Science and Engineering, 2021,8(2): 1009-1018.
[33]	LIN L J , TIAN Y C , LIU Y . A blockchainbased privacy-preserving recommendation mechanism[C]// Proceedings of 2021 IEEE 5th International Conference on Cryptography,Security and Privacy. Piscataway:IEEE Press, 2021: 74-78.
[34]	UMEKWUDO J O , SHIM J . Blockchain technology for mobile applications recommendation systems[J]. The Journal of Society for e-Business Studies, 2019,24(3): 129-142.
[35]	ARIF Y , NOPEMBER I T S , NURHAYATI H ,et al. Blockchain-based data sharing for decentralized tourism destinations recommendation system[J]. International Journal of Intelligent Engineering and Systems, 2020,13(6): 472-486.
[36]	陈亚辉, 吴基成, 孙澜 . 金融用户精准可信推荐研究[J]. 广西质量监督导报, 2019(11): 195-196.
	CHEN Y H , WU J C , SUN L . Research on accurate and credible recommendation for financial users[J]. Guangxi Quality Supervision Guide Periodical, 2019(11): 195-196.
[37]	YAN B W , YU J G , WANG Y ,et al. Blockchainbased service recommendation supporting data sharing[C]// Proceedings of 2020 International Conference on Wireless Algorithms,Systems,and Applications. Cham:Springer International Publishing, 2020: 580-589.
[38]	LISI A , DE SALVE A , MORI P ,et al. Rewarding reviews with tokens:an Ethereum-based approach[J]. Future Generation Computer Systems, 2021,120: 36-54.
[39]	YAN B W , DONG A M , CHAI B B ,et al. Blockchain-assisted collaborative service recommendation scheme with data sharing[J]. IEEE Access, 2021,9:4087140883.
[40]	董学文, 刘昊哲, 乔慧 ,等. 支持冷启动用户推荐的区块链服务发布方案[J]. 通信学报, 2021,42(1): 57-66.
	DONG X W , LIU H Z , QIAO H ,et al. Blockchain-based service publishing scheme with recommendation for cold start users[J]. Journal on Communications, 2021,42(1): 57-66.
[41]	黎孟雄, 李杨 . 基于区块链的教育资源智能分发平台研究[J]. 长沙大学学报, 2020,34(2): 49-54.
	LI M X , LI Y . Research on intelligent distribution platform of education resource based on blockchain[J]. Journal of Changsha University, 2020,34(2): 49-54.
[42]	ARORA M , CHOPRA A B , DIXIT V S . An approach to secure collaborative recommender system using artificial intelligence,deep learning,and blockchain[C]// Proceedings of 2018 Intelligent Communication,Control and Devices. Singapore:Springer Singapore, 2020: 483-495.
[43]	ABBAS K , AFAQ M , AHMED KHAN T ,et al. A blockchain and machine learningbased drug supply chain management and recommendation system for smart pharmaceutical industry[J]. Electronics, 2020,9(5): 852.
[44]	WANG S , HUANG C C , LI J J ,et al. Decentralized construction of knowledge graphs for deep recommender systems based on blockchain-powered smart contracts[J]. IEEE Access, 2019,7: 136951-136961.
[45]	CAI W H , DU X , XU J L . A personalized QoS prediction method for web services via blockchain-based matrix factorization[J]. Sensors, 2019,19(12): 2749.
[46]	SRIDEVI S , KARPAGAM G R , KUMAR B V . Incorporating blockchain for semantic web service selection (SWSS) method[J]. Sādhanā, 2021,46(2): 1-14.
[47]	PORKODI S , KESAVARAJA D . A trustbased recommender system built on IoT blockchain network with cognitive framework[M]// Recommender system with machine learning and artificial intelligence:practical tools and applications in medical,agricultural and other industries. Hoboken: John Wiley ＆Sons,Inc., 2020: 293-311.
[48]	LISI A , DE SALVE A , MORI P ,et al. A smart contract based recommender system[C]// Proceedings of 2019 International Conference on the Economics of Grids,Clouds,Systems,and Services. Cham:Springer International Publishing, 2019: 29-42.
[49]	YEH T Y , KASHEF R . Trust-based collaborative filtering recommendation systems on the blockchain[J]. Advances in Internet of Things, 2020,10(4): 37-56.
[50]	LISI A , DE SALVE A , MORI P ,et al. Practical application and evaluation of atomic swaps for blockchain-based recommender systems[C]// Proceedings of the 3rd International Conference on Blockchain Technology and Applications. New York:ACM Press, 2020: 67-74.
[51]	施巍松, 张星洲, 王一帆 ,等. 边缘计算:现状与展望[J]. 计算机研究与发展, 2019,56(1): 69-89.
	SHI W S , ZHANG X Z , WANG Y F ,et al. Edge computing:state-of-theart and future directions[J]. Journal of Computer Research and Development, 2019,56(1): 69-89.

主要解决问题	代表文献	区块链的应用方式
数据安全和隐私保护	文献[10,27-35]	· 区块链使用户的数据信息存储在多个节点上，避免恶意攻击；
		· 用户拥有数据的完全控制权，可对敏感数据加密上链，仅授权方可解密，并且随时可终止授权；
		·区块链上的用户通过账户地址参与交易，无法与真实身份对应；
		·每笔交易信息都记录在区块链上，保护数据不被滥用
数据共享	文献[36-39]	· 区块链上的各节点可自由交易，无须中介机构，通过加密技术对交易细节加密，结合智能合约保证交易高效安全完成；
		· 通过区块链上的智能合约预设规则，对共享数据的用户进行奖励分配
数据可信	文献[30,40-47]	·通过区块链共识机制对用户提交的数据进行验证和记录；
		· 由于共识机制的作用，数据一旦通过验证并写入区块链后就难以篡改；
		· 通过区块链上的智能合约预设规则，对提供有效数据的用户和矿工给予代币激励
推荐透明度	文献[27,48-50]	· 用户、物品、用户评分等都存储在区块链上，计算物品分数的算法存储在智能合约中，用户可选择特定算法来计算物品分数；
		· 区块链与推荐系统深度融合，构建难以篡改的模型，跟踪推荐过程

作者	推荐性能	安全性能	效率性能
杨立等人^[29]	推荐转化率	隐私性、透明性、可验证性、可信性	存储可扩展性（定量）
		（定性）
赵子军等人^[28]	—	安全性（定性）	通信开销、计算开销（定量）
Casino F等人^[31]	预测准确度	隐私性	局部敏感哈希（locality sensitive hashing，LSH）方法的效率（定量）
Li X L等人^[30]	预测准确度	隐私性、安全性（定性）	—
Bosri R等人^[32]	—	隐私性、完整性、可验证性（定性）	计算开销（推荐生成时间，定量）
Lisi A等人^[48]	—	—	吞吐量、燃料消耗、可扩展性（定量）
Wang S等人^[44]	推荐有效性（案例研究、	—	—
	问卷调查）
Yan B W等人^[37]	预测准确度	隐私性、难以篡改（定性）	燃料消耗
董学文等人^[40]	预测准确度	—	吞吐量（定量）
Yeh T Y等人^[49]	预测准确度	—	燃料消耗
Lisi A等人^[38]	—	安全性（定性）	燃料消耗、吞吐量、计算延迟时间（定量）
Sridevi S等人^[46]	预测准确度	—	—
Yan B W等人^[39]	预测准确度	难以篡改、完整性、避免单点故障（定性）	内存消耗、吞吐量、计算延迟时间（定量）
Lin L J等人^[33]	预测准确度	隐私性	—
Cai W H等人^[45]	预测准确度	—	—