Please wait a minute...
Advanced Search
现代图书情报技术  2015, Vol. 31 Issue (6): 93-100     https://doi.org/10.11925/infotech.1003-3513.2015.06.14
  研究论文 本期目录 | 过刊浏览 | 高级检索 |
电商用户“状态-行为”建模及其在商品信息搜索行为分析的应用
袁兴福, 张鹏翼, 王军
北京大学信息管理系 北京 100871
“State-Behavior” Modeling and Its Application in Analyzing Product Information Seeking Behavior of E-commerce Websites Users
Yuan Xingfu, Zhang Pengyi, Wang Jun
Department of Information Management, Peking University, Beijing 100871, China
全文: PDF (1084 KB)   HTML  
输出: BibTeX | EndNote (RIS)      
摘要 

目的】对用户在电商网站进行信息查询、商品比较、购物决策过程中产生的多种类型的信息行为进行系统性描述和精确建模。【方法】提出一种描述用户信息行为的序列特征、时间特征、内容特征的“状态-行为”模型。实验数据来自4 710位用户在2013年5月访问淘宝网的浏览器日志, 在用户访问页面类型切换与用户行为类型之间建立映射, 得到用户的行为序列, 进一步抽象用户会话的“状态-行为”, 在会话层面上表示、汇集用户行为特征。【结果】应用上述建模方法对用户行为序列、时间特征和内容复杂度进行建模、聚类, 得到8类具有显著特征的用户: 行动迅捷的搜索者、信息浏览漫步者、营销信息依赖者、个人资料管理者、工作日会话产生者、休息日会话产生者、晚间会话产生者、非常规时间访问者。【局限】在日志与行为之间建立会话层进行建模, 可能导致会话层抽取的误差叠加而降低精度, 因此需要特别控制会话层的误差。【结论】该方法可以描述更丰富的电商用户信息行为特征, 用户聚类的结果可用于指导网站推荐与营销方案的制定, 对于研究电商网站用户与实现个性化推荐具有参考价值。

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
袁兴福
张鹏翼
王军
关键词 访问日志商品信息搜索行为序列电商网站    
Abstract

[Objective] This research aims to develop an approach to model and describe the user information behaviors during information seeking, product comparison, and decision-making process more systematically and precisely. [Methods] This paper proposes a user “state-behavior” model including sequential, temporal, and content features. Test data set includes the click-through log data of 4 710 users from taobao.com. The user behavior sequences are established by mapping page types and user behaviors, and then used as features to model users' “status-behavior” at the session level. [Results] Classification using the “state-behavior” model resulted 8 user groups with significant features, including swift searchers, serendipitous browsers, promotion-driven users, personal information maintainers, weekday-active users, weekend-active users, night-active users, and irregular users. [Limitations] Adding a session layer between logs and user behavior may cause accumulation of classification errors at the session level into the behavior level. [Conclusions] The results show that this model is able to capture the behavior sequence more precisely. The classification of users may be used in guiding personalized recommendation and marketing plans for e-commerce Websites.

Key wordsClick-through logs    Product information seeking    Action sequence    E-commerce Websites
收稿日期: 2014-12-12      出版日期: 2015-07-08
:  G250.2  
基金资助:

本文系国家自然科学基金项目“面向电商生态平衡的导购机制研究”(项目编号:71373016)的研究成果之一。

通讯作者: 张鹏翼, ORCID: 0000-0003-0624-6776, E-mail: pengyi@pku.edu.cn。     E-mail: pengyi@pku.edu.cn
作者简介: 作者贡献声明: 袁兴福: 数据处理、分析, 完成建模实验, 论文初稿撰写; 张鹏翼: 研究定位、框架设计, 论文修改及最终版本修订; 王军: 研究方案设计, 论文修改。
引用本文:   
袁兴福, 张鹏翼, 王军. 电商用户“状态-行为”建模及其在商品信息搜索行为分析的应用[J]. 现代图书情报技术, 2015, 31(6): 93-100.
Yuan Xingfu, Zhang Pengyi, Wang Jun. “State-Behavior” Modeling and Its Application in Analyzing Product Information Seeking Behavior of E-commerce Websites Users. New Technology of Library and Information Service, 2015, 31(6): 93-100.
链接本文:  
https://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/10.11925/infotech.1003-3513.2015.06.14      或      https://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/Y2015/V31/I6/93

[1] 中国互联网络信息中心. 中国互联网络发展状况统计报告 [R/OL]. [2015-03-14]. https://www.cnnic.net.cn/hlwfzyj/hlwxzbg/ hlwtjbg/201502/P020150203548852631921.pdf. (China Internet Network Information Center. Statistical Report on Internet Development in China [R/OL]. [2015-03-14]. https://www. cnnic.net.cn/hlwfzyj/hlwxzbg/hlwtjbg/201502/P020150203548852631921.pdf.)
[2] 纪征. 基于用户兴趣模型的电子商务网站推荐技术比较及启示[J]. 图书情报工作, 2010, 54(16): 138-140. (Ji Zheng. Recommendation Technology Based on User's Interest Model for the E-commerce Site [J]. Library and Information Service, 2010, 54(16): 138-140.)
[3] Ji J, Liu C, Sha Z, et al. Online Personalized Recommen­dation Based on a Multilevel Customer Model [J]. International Journal of Pattern Recognition and Artificial Intelligence, 2005, 19(7): 895-916.
[4] Montgomery A L, Li S, Srinivasan K, et al. Modeling Online Browsing and Path Analysis Using Clickstream Data [J]. Marketing Science, 2004, 23(4): 579-595.
[5] 马晓艳, 唐雁. 一种基于用户浏览路径的Web用户聚类方法[J]. 西南师范大学学报: 自然科学版, 2009, 34(3): 93-97. (Ma Xiaoyan, Tang Yan. Clustering Web Users Based on Users' Browsing Path [J]. Journal of Southwest China Normal University: Natural Science Edition, 2009, 34(3): 93-97.)
[6] 张波, 巫莉莉, 周敏. 基于Web使用挖掘的用户行为分析[J]. 计算机科学, 2006, 33(8): 213-214. (Zhang Bo, Wu Lili, Zhou Min. The Analysis of User Behavior Based on Web Usage Mining [J]. Computer Science, 2006, 33(8): 213-214.)
[7] Benevenuto F, Rodrigues T, Cha M, et al. Characterizing User Behavior in Online Social Networks [C]. In: Proceedings of the 9th ACM SIGCOMM Conference on Internet Measure­ment Conference. ACM, 2009.
[8] 王微微, 夏秀峰, 李晓明. 一种基于用户行为的兴趣度模型[J]. 计算机工程与应用, 2012, 48(8): 148-151. (Wang Weiwei, Xia Xiufeng, Li Xiaoming. Personal Interest Degree Model Based on Consumer Behavior [J]. Computer Engineering and Applications, 2012, 48(8): 148-151.)
[9] 伍大清, 阳小华, 马家宇, 等. 基于隐式反馈的用户兴趣漂移方法[J]. 计算机应用与软件, 2010, 27(9): 88-90. (Wu Daqing, Yang Xiaohua, Ma Jiayu, et al. Method of Drifting User's Interests Based on Implicit Feedback [J]. Computer Applications and Software, 2010, 27(9): 88-90.)
[10] 丁宏飞. 个性化电子商务系统中用户兴趣模型的研究[D]. 广州: 暨南大学, 2008. (Ding Hongfei. The Study of User Interest Model in Personalized E-commerce System [D]. Guangzhou: Jinan University, 2008.)
[11] Kohavi R, Parekh R. Ten Supplementary Analyses to Improve E-commerce Web Sites [C]. In: Proceedings of the 5th Workshop on Knowledge Discovery in the Web. Springer- Verlag, 2003.
[12] 赵银春, 付关友, 朱征宇. 基于Web浏览内容和行为相结合的用户兴趣挖掘[J]. 计算机工程, 2005, 31(12): 93-94, 198. (Zhao Yinchun, Fu Guanyou, Zhu Zhengyu. User Interest Mining of Combining Web Content and Behavior Analysis [J]. Computer Engineering, 2005, 31(12): 93-94, 198.)
[13] Moe W W. Buying, Searching, or Browsing: Differentiating Between Online Shoppers Using In-store Navigational Clickstream [J]. Journal of Consumer Psychology, 2003, 13(1): 29-39.
[14] 徐赟, 张盼, 丁婕. 只逛不买的电子商务用户分析——以淘宝网为例[J]. 信息系统学报, 2012(2): 64-75. (Xu Yun, Zhang Pan, Ding Jie. Analysis of “Browsing but Non- shopping” E-commerce Users — An Empirical Research Based on Taobao.Com [J]. China Journal of Information Systems, 2012(2): 64-75.)
[15] 王开选. 用户模型的结构表示及其应用研究[D]. 太原: 山西大学, 2005. (Wang Kaixuan. The Structural Representation and Application of User Profile [D]. Taiyuan: Shanxi University, 2005.)
[16] Cantador I, Bellogín A, Vallet D. Content-based Recommendation in Social Tagging Systems [C]. In: Proceedings of the 4th ACM Conference on Recommender Systems. ACM, 2010.
[17] 袁兴福, 张鹏翼, 刘洪莲, 等. 基于点击流的电商用户会话建模[J]. 图书情报工作, 2015, 59(1): 119-126. (Yuan Xingfu, Zhang Pengyi, Liu Honglian, et al. Modeling E-commerce User Session Behaviors Based on Click-through Sequence [J]. Library and Information Service, 2015, 59(1): 119-126.)

[1] 张学宏. 北京大学图书馆的主页日志分析[J]. 现代图书情报技术, 2005, 21(5): 81-83.
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