摘要
如何让消费者在评分信息不完整,消费者偏好不一致和评价标准不一致的情况下从海量在线商品中做出正确选择,成为消费者关注的问题.为此,提出利用Copeland社会选择理论的在线商品群体评价.首先基于消费者历史评分间的相似性填充不完整消费者-商品评分矩阵;其次建立每个消费者对在线商品的偏好关系,并表达为商品-商品偏好比较矩阵;最后利用社会选择理论的Copeland方法将偏好比较矩阵中的商品被偏好次数两两成对比较,并记录比较的赢输差值作为Copeland评价值.评价值越高,则在线商品群体评价越高.理论分析验证了方法满足在线商品评价的基本准则.实验结果也表明方法可有效解决不同用户间评分不可比较的问题,并提高在线商品群体评价的操纵复杂性.
Faced with mass online commodities how to make the right choice has become a consumer concern. Under the circumstance of the score information is incomplete,the consumer preference is inconsistent and the evaluation criteria are inconsistent. In order to solve this problem,a group evaluation method for online commodities using Copeland social choice theory is proposed. Firstly,the incomplete consumer-product ratings matrix were filled up based on the similarity between the consumer history scores; And then establish the preference relationship of each consumer to the online commodities and express it as product-product preference comparison matrix; Finally,using Copeland social choice theory to compare the commodity preferences one by one,and recorded as the Copeland evaluation value. The theoretical analysis verifies that the method meets the basic criteria of online commodity evaluation. The experimental results also show that the method can effectively solve the problem of unmatched score among different users and improve the manipulation complexity of online commodities group evaluation.
作者
殷岩
付晓东
刘骊
岳昆
刘利军
冯勇
YIN Yan;FU Xiao-dong;LIU Li;YUE Kun;LIU Li-jun;FENG Yong(Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, China;Faculty of Aeronautics, Kunming University of Science and Technology, Kunming 650500, China;School of Information Science and Engineering, Yunnan University, Kunming 650091, China)
出处
《小型微型计算机系统》
CSCD
北大核心
2018年第6期1201-1207,共7页
Journal of Chinese Computer Systems
基金
国家自然科学基金项目(61462056
61472345
61462051
81560296
61662042)资助
云南省应用基础研究计划项目(2014FA028
2014FA023)资助
关键词
社会选择理论
在线商品
群体评价
偏好关系
在线评分
social choice theory
online commodities
group evaluation
preference relation
online rating
作者简介
殷岩,女,1990年生,硕士研究生,研究方向为服务计算、决策理论与方法;;付晓东(通信作者),男,1975年生,博士,教授,CCF高级会员,研究方向为服务计算、决策理论与方法;E—mail:xiaodong_fu@hotmail.com;刘骊,女,1979年生,博士,副教授,研究方向为服务计算、智能家居;;岳昆,男,1979年生,博士,教授,博士生导师,研究方向为大数据服务;;刘利军,男,1978年生,硕士,讲师,研究方向为智能医疗服务;;冯勇,男,1975年生,博士,副教授,研究方向为智能传感网络.