国内电子商务网站推荐系统信息服务质量比较研究——以淘宝、京东、亚马逊为例

doi:10.13266/j.issn.0252-3116.2016.23.013

图书情报工作 ›› 2016, Vol. 60 ›› Issue (23): 97-110.DOI: 10.13266/j.issn.0252-3116.2016.23.013

国内电子商务网站推荐系统信息服务质量比较研究——以淘宝、京东、亚马逊为例

洪亮^1,2, 任秋圜¹, 梁树贤¹

1 武汉大学信息管理学院武汉 430072;
2 武汉大学信息资源研究中心武汉 430072

收稿日期:2016-09-14 修回日期:2016-11-17 出版日期:2016-12-05 发布日期:2016-12-05
作者简介:洪亮(ORCID:0000-0002-1466-9843),副教授,E-mail:hong@whu.edu.cn;任秋圜(ORCID:0000-0002-9069-7037),本科生;梁树贤(ORCID:0000-0002-9183-235X),本科生。
基金资助:
本文系教育部人文社会科学重点研究基地重大项目“大数据资源的语义表示与组织研究——面向文化遗产领域”（项目编号：16JJD870002）和武汉大学人文社会科学青年学者学术发展计划学术团队项目研究成果之一。

A Comparative Study of Information Service Quality of E-commerce Sites' Recommender Systems-Take Taobao, Jingdong and Amazon as Examples

Hong Liang^1,2, Ren Qiuyuan¹, Liang Shuxian¹

1 School of Information Management, Wuhan University, Wuhan 430072;
2 Center for the Studies of Information Resources, Wuhan University, Wuhan 430072

Received:2016-09-14 Revised:2016-11-17 Online:2016-12-05 Published:2016-12-05

摘要/Abstract

摘要：

[目的/意义]推荐系统已经成为电子商务网站的重要组成部分之一，为用户提供多种形式的信息推荐服务。国内以淘宝、京东和亚马逊为代表的电子商务网站的推荐系统采用不同的技术架构和多种热点推荐技术，并且越来越重视信息服务的质量。对推荐系统服务质量进行比较研究，能够进一步推动电子商务推荐系统的发展。[方法/过程]首先，从准确性、时效性、新颖性三个技术指标对比以上推荐系统的技术架构对于推荐服务质量的影响；其次，以用户体验作为信息服务质量评价的基础，对182名受访者进行热点技术的认可度调查，研究热点技术对推荐服务质量的影响；最后，对功能模块的用户体验情况进行调查和比较分析。[结果/结论]在这些研究、调查和分析的基础上，给出电子商务推荐系统使用的技术架构和热点技术，以及改进功能模块设计的对策，以进一步提升推荐系统的信息服务质量。

关键词: 推荐系统, 用户体验, 电子商务, 信息服务

Abstract:

[Purpose/significance] Recommender system has already been one of the most important parts of an e-commerce site and provides users with a variety of forms of information recommendation service.Nowadays, recommender systems in e-commerce sites such as Taobao, Jingdong and Amazon have adopted different frameworks and a variety of hotspot recommendation technologies,and paid more and more attention to quality of information service. [Method/process] Therefore,firstly,we take the user experience as the basis for evaluating quality of information service and compare the influence of frameworks of the recommender systems mentioned above on the quality of recommendation service.Secondly, we study the research hotspots and the trend of the RecSys in recent 5 years, based on which we carry out an investigation of users' expectation and preference of these hotspots.Lastly, we conduct an evaluating experiment of user experience in e-commerce recommendation aiming at these e-commerce sites and make a comparative analysis. [Result/conclusion] With the help of the research, investigation and experiment mentioned above, finally we come up with some strategies onhow to optimize the framework of recommender systems, pick up suitable hotspot recommendation technologies, and perfect the recommendation modules in e-commerce sites, all of which can apparently improve the quality of information service of e-commerce sites' recommender systems.

Key words: recommender system, user experience, e-commerce, information service

中图分类号:

G250

洪亮, 任秋圜, 梁树贤. 国内电子商务网站推荐系统信息服务质量比较研究——以淘宝、京东、亚马逊为例[J]. 图书情报工作, 2016, 60(23): 97-110.

Hong Liang, Ren Qiuyuan, Liang Shuxian. A Comparative Study of Information Service Quality of E-commerce Sites' Recommender Systems-Take Taobao, Jingdong and Amazon as Examples[J]. LIS, 2016, 60(23): 97-110.

参考文献

[1] 蔺丰奇,刘益.信息过载问题研究述评[J].情报理论与实践,2007(5):710-714.
[2] 胡昌平,周怡.数字化信息服务交互性影响因素及服务推进分析[J].中国图书馆学报,2008(6):53-57.
[3] 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(2):350-362.
[4] 景民昌.从ACM RecSys'2014国际会议看推荐系统的热点和发展[J].现代情报,2015(4):41-45.
[5] 宋辉.电子商务推荐系统用户采纳影响因素研究[D].哈尔滨:哈尔滨工业大学,2011.
[6] ADOMAVICIUS G, TUZHILIN A. Toward the next generation of recommender systems:asurvey of the state-of-the-art and possible extensions[J].IEEE transactions on knowledge and data engineering, 2005,17(6):734-749.
[7] 项亮.推荐系统实践[M].北京:人民邮电出版社,2012:44-59.
[8] LU J, WU D, MAO M, et al. Recommender system application developments[J].Decision support systems, 2015,74(C):12-32.
[9] SU X, KHOSHGOFTAAR T. A survey of collaborative filtering techniques[J].Advances in artificial intelligence, 2009, 2009(4):1-19.
[10] 李杰,徐勇,王云峰,等.面向个性化推荐的强关联规则挖掘[J].系统工程理论与实践,2009(8):144-152.
[11] STECK H. Gaussian ranking by Mmatrixfactorization[C]//WERTHNER H, et al. Proceedings of the 9th ACM conference on recommender systems(RecSys'15). New York:ACM, 2015:115-122.
[12] BHAGAT S, WEINSBERG U, IOANNIDIS S, et al. Recommending with an agenda:active learning of private attributes using matrix factorization[C]//KOBSA A, et al. Proceedings of the 8th ACM conference on recommender systems(RecSys'14). New York:ACM, 2014:65-72.
[13] VANCHINATHAN H, NIKOLIC I, BONA F, et al. Explore-exploit in top-N recommender systems via Gaussian processes[C]//KOBSA A, et al. Proceedings of the 8th ACM conference on recommender systems(RecSys'14). New York:ACM, 2014:225-232.
[14] BABAS K, CHALKIADAKIS G, TRIPOLITAKIS E. You are what you consume:a Bayesian method for personalized recommendations[C]//YANG Q, et al. Proceedings of the 7th ACM conference on recommender systems(RecSys'13). New York:ACM, 2013:221-228.
[15] SCHELTER S, BODEN C, MARKL V. Scalable similarity-based neighborhood methods with MapReduce[C]//CUNNINGHAM P, et al. Proceedings of the 6th ACM conference on recommender systems(RecSys'12). New York:ACM, 2012:163-170.
[16] 沈旺,马一鸣,李贺.基于情境感知的用户推荐系统研究综述[J].图书情报工作,2015,59(21):128-138.
[17] VERSTREPEN K, GOETHALS B. Top-N recommendation for shared accounts[C]//WERTHNER H, et al. Proceedings of the 9th ACM conference on recommender systems(RecSys'15). New York:ACM, 2015:59-66.
[18] LU H, CAVERLEE J. Exploiting geo-spatial preference for personalized expert recommendation[C]//WERTHNER H, et al. Proceedings of the 9th ACM conference on recommender systems(RecSys'15). New York:ACM, 2015:67-74.
[19] HARIRI N, MOBASHER B, BURKE R. Context adaptation in interactive recommender systems[C]//KOBSA A, et al. Proceedings of the 8th ACM conference on recommender systems(RecSys'14). New York:ACM, 2014:41-48.
[20] HARIRI N, MOBASHER B, BURKE R. Query-driven context aware recommendation[C]//YANG Q, et al. Proceedings of the 7th ACM conference on recommender systems(RecSys'13). New York:ACM, 2013:9-16.
[21] HARPER F, XU F, KAUR H, et al. Putting users in control of their recommendations[C]//WERTHNER H, et al. Proceedings of the 9th ACM conference on recommender systemsconference on recommender systems(RecSys'15). New York:ACM, 2015:3-10.
[22] EKSTRAND M, HARPER F, WILLEMSEN M, et al. User perception of differences in recommender algorithms[C]//KOBSA A, et al. Proceedings of the 8th ACM conference on recommender systemsconference on recommender systems(RecSys'14). New York:ACM, 2014:161-168
[23] CREMONESI P, GARZOTTTO F, TURRIN R. User effort vs. accuracy in rating-based elicitation[C]//CUNNINGHAM P, et al. Proceedings of the 6th ACM conference on recommender systems(RecSys'12). New York:ACM, 2012:27-34.
[24] SPARLING E, SEN S. Rating:how difficult is it?[C]//MOBASHER B, et al. Proceedings of the 5th ACM conference on recommender systems(RecSys'11). New York:ACM, 2011:149-156.
[25] MCAULEY J, LESKOVEC J. Hidden factors and hidden topics:understanding rating dimensions with review text[C]//YANG Q, et al. Proceedings of the 7th ACM conference on recommender systems(RecSys'13). New York:ACM, 2013:165-172.
[26] YI X, HONG L, ZHONG E, et al. Beyond clicks:dwell time for personalization[C]//KOBSA A, et al. Proceedings of the 8th ACM conference on recommender systems(RecSys'14). New York:ACM, 2014:113-120.
[27] OSTUNI V, NOIA T, SCIASCIO E, et al. Top-N recommendations from implicit feedback leveraging linked open data[C]//YANG Q, et al. Proceedings of the 7th ACM conference on recommender systems(RecSys'13). New York:ACM, 2013:85-92.
[28] CHANEY A, BLEI D, ELIASSI-RAD T. A probabilistic model for using social networks in personalized item recommendation[C]//WERTHNER H, et al.Proceedings of the 9th ACM conference on recommender systems(RecSys'15). New York:ACM, 2015:43-50.
[29] DIAZ-AVILES E, DRUMOND L, SCHMIDT-THIEME L, et al. Real-time top-N recommendation in social streams[C]//CUNNINGHAM P, et al. Proceedings of the 6th ACM conference on recommender systems(RecSys'12). New York:ACM, 2012:59-66.
[30] KNIJNENBURG B, BOSTANDJIEV S, O'DONOVAN J, et al. Inspectability and control in social recommenders[C]//CUNNINGHAM P, et al. Proceedings of the 6th ACM conference on recommender systems(RecSys'12). New York:ACM, 2012:43-50.
[31] AHARON M, ANAVA O, AVIGDOR-ELGRABLI N, et al. ExcUseMe:asking users to help in item cold-start recommendations[C]//WERTHNER H, et al. Proceedings of the 9th ACM conference on recommender systems(RecSys'15). New York:ACM, 2015:83-90.
[32] BARJASTEH I, FORSATI R, MASROUR F, et al. Cold-start item and user recommendation with decoupled completion and transduction[C]//WERTHNER H, et al. Proceedings of the 9th ACM conference on recommender systems(RecSys'15). New York:ACM, 2015:91-98.
[33] LIU N, MENG X, LIU C, et al. Wisdom of the better few:cold start recommendation via representative based rating elicitation[C]//MOBASHER B, et al. Proceedings of the 5th ACM conference on recommender systems(RecSys'11). New York:ACM, 2011:37-44.
[34] SAVESKI M, MANTRACH A. Item cold-start recommendations:learning local collective embeddings[C]//KOBSA A, et al. Proceedings of the 8th ACM conference on recommender systems(RecSys'14). New York:ACM, 2014:89-96.
[35] STECK H. Item popularity and recommendation accuracy[C]//MOBASHER B, et al. Proceedings of the 5th ACM conference on recommender systems(RecSys'11). New York:ACM, 2011:125-132.
[36] VARGAS S, CASTELLS P. Rank and relevance in novelty and diversity metrics for recommender systems[C]//MOBASHER B, et al. Proceedings of the 5th ACM conference on recommender systems(RecSys'11). New York:ACM, 2011:109-116.
[37] 魏虎.推荐系统@淘宝[OL].[2016-04-10].http://wenku.baidu.com/view/4f1a38f54693daef5ef73db2.html.
[38] 赵斌强.个性化推荐技术在广告中的应用[OL].[2016-04-10]. http://wenku.it168.com/d_001181071.shtml.
[39] 周建丁.订单贡献率10%,京东个性化推荐系统持续优化的奥秘[OL].[2016-04-10]. http://m.csdn.net/article/2015-04-15/2824476.
[40] 刘尚堃.京东数据驱动下的个性化推荐系统[OL].[2016-04-10]. http://www.36dsj.com/archives/36841.
[41] LINDEN G, SMITH B, YORK J. Amazon.com recommendations:item-to-item collaborative filtering[J]. IEEE Internet computing, 2003,7(1):76-80.

国内电子商务网站推荐系统信息服务质量比较研究——以淘宝、京东、亚马逊为例

A Comparative Study of Information Service Quality of E-commerce Sites' Recommender Systems-Take Taobao, Jingdong and Amazon as Examples

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	邓胜利, 孙瑾杰. 图书馆参与虚假健康信息治理的价值、阻滞因素和实现路径[J]. 图书情报工作, 2022, 66(9): 14-22.
[2]	郑淞尹, 谈国新. 景点文化资源标签自动生成与应用研究[J]. 图书情报工作, 2022, 66(7): 132-143.
[3]	梁美宏, 孙清玉, 林峥, 陶媛媛. 面向重点团队的H大学图书馆知识产权信息服务案例研究[J]. 图书情报工作, 2022, 66(6): 34-42.
[4]	沈东婧, 李莎, 姚远, 周成效, 许咏丽, 江晓波, 顾燕婷. 动能转换视角下图书馆信息服务创新提质增效案例与对策研究[J]. 图书情报工作, 2022, 66(6): 43-50.
[5]	刘裕, 周毅, 农顔清. 网络信息服务平台用户个人信息安全风险及其治理——基于117个APP隐私政策文本的内容分析[J]. 图书情报工作, 2022, 66(5): 33-43.
[6]	张公一, 郭鑫. 价值共创视角下企业信息服务体系构建与发展策略[J]. 图书情报工作, 2022, 66(5): 53-62.
[7]	孟猛, 朱庆华. 移动视觉搜索用户体验模型构建与实证研究[J]. 图书情报工作, 2022, 66(5): 80-92.
[8]	陆颖颖, 孙裕彤, 张瑶, 李旭光. 人工智能、机器学习、自动化和机器人技术对信息行业的影响——2021年CILIP专题研讨会综述与启示[J]. 图书情报工作, 2022, 66(19): 143-152.
[9]	刘一鸣, 朱萍萍. 国外公共图书馆健康信息服务项目的研究与启示——以EIFL"公共图书馆服务创新项目"为例[J]. 图书情报工作, 2022, 66(18): 140-150.
[10]	罗祺姗, 王梦圆. 图书馆新冠专题资源应急保障成效评估研究——以中国科学院文献情报中心为例[J]. 图书情报工作, 2022, 66(14): 29-36.
[11]	吕源, 陈慧琪, 刘敏榕. 高校知识产权信息服务内容体系构建研究[J]. 图书情报工作, 2022, 66(12): 59-67.
[12]	卢文辉. 学位论文引文视角下的硕士生学术文献信息资源使用行为特征研究[J]. 图书情报工作, 2022, 66(10): 131-142.
[13]	赵乃瑄, 许睿. 日本高校知识产权信息服务特点与启示[J]. 图书情报工作, 2021, 65(8): 114-121.
[14]	崔林. 中美高校图书馆专利信息服务比较研究与启示[J]. 图书情报工作, 2021, 65(4): 40-48.
[15]	宋玉梅, 严哲, 朱琳, 罗钧. 微信视域下高校知识产权信息服务的现状与发展对策研究[J]. 图书情报工作, 2021, 65(3): 51-60.