电信科学 ›› 2014, Vol. 30 ›› Issue (9): 82-86.doi: 10.3969/j.issn.1000-0801.2014.09.011

• 研究与开发 • 上一篇    下一篇

基于社会网络协同过滤的社会化电子商务推荐研究

琚春华1,2,鲍福光1,3,许翀寰1,3   

  1. 1 浙江工商大学现代商贸研究中心 杭州310018
    2 浙江工商大学计算机与信息工程学院 杭州310018
    3 浙江工商大学工商管理学院 杭州310018
  • 出版日期:2014-09-20 发布日期:2017-07-05
  • 基金资助:
    心积极资助课题成果,国家自然科学基金资助项目;国家教育部博士点基金资助项目;社科基金资助项目;浙江省自然科学基金资助项目

Researcb on Social Network Collaborative Filtering Based E-commerce Recommending

Chunhua Ju1,2,Fuguang Bao1,3,Chonghuan Xu1,3   

  1. 1 Contemporary Business and Trade Research Center of Zhejiang Gongshang University, Hangzhou 310018, China
    2 School of Computer Science and Information Engineering, Zhejiang Gongshang University, Hangzhou 310018, China
    3 School of Business Administration, Zhejiang Gongshang University, Hangzhou 310018, China
  • Online:2014-09-20 Published:2017-07-05

摘要:

随着社会网络关系的不断复杂化,商品是否推荐成功,除了基于商品本身的特征外,还受社会网络关系的影响。很多用户更加信任来自朋友的推荐,而非机器通过单因素计算出来的推荐结果。因此,设计了一个融入社会网络关系的电子商务推荐系统。其中,构建了社会网络关系强度、兴趣偏好强度和商品流行性与声望强度3个关键因子,每个一级因子又由若干个二级因子构成。实验结果验证了社会网络关系会对其中成员的网购等网络行为产生影响,构建的基于社会网络的电子商务推荐策略的效果比其他单因素推荐策略好且稳定,具有很好的实际应用效果。

关键词: 社会网络强度, 兴趣偏好强度, 声望强度, 层次分析法, 协同过滤, 电子商务

Abstract:

With the development of the social network relation, whether the recommendation is successful, is not only depending on the characteristics of goods, but also influenced by social network relationship. Many users more trust from their friends'recommendation, rather than the machine recommended by single factor calculated results. Therefore, an E-commerce recommending system based on social network collaborative filtering was proposed. In the system, the crucial factors of social network relation intensity, interest preference intensity and production popularity with reputation intensity were set.And each first-level factor was composed of some second-level factors.Experimental results verify that social network relationships will affect users shopping behaviors and so on. In addition, the recommendation method based on social network is superior to other approaches and has better application effect.

Key words: social network relation intensity, interest preference intensity, reputation intensity, AHP, collaborative, filtering, E-commerce

No Suggested Reading articles found!