基于网络客户评论的产品口碑排序方法

摘要

电子商务时代,产品的网络口碑已成为消费者做购买决策的重要参考依据.本文利用客户评论信息,依据产品的评分及产品之间的对比投票数据,提出了一个新的产品口碑排序方法.首先利用产品两两间的对比投票计算各自的相对口碑,再采用贝叶斯平均方法修正原始客户评分,然后将二者结合得到产品的总口碑,进而对产品的网络口碑进行排序.实验数据采自第三方点评网站中的产品对比投票数据,实验结果表明本文提出的产品口碑排序方法具有较高的支持度,且与产品销量排序的相关性也很高.%In the era of E-commerce,online word-of-mouth (WOM) of products is more and more important for consumers to make purchase decisions when shopping online.This paper proposes an effective WOM ranking method by two kinds of consumer reviews dataset,such as means of ratings and comparative votes on products.It firstly computes relative WOM based on comparative votes,and then modifies the original ratings by the method of True Bayesian Average.Afterwards it combines relative WOM ratings and modified ratings to form the summarized WOM ratings for all products.At last a ranking of all products can be derived based on summarized WOM ratings.Evaluation on the proposed WOM ranking method is conducted by using the real world datasets coming from a famous third party review website in China.Empirical results show that the WOM ranking list obtained by our approach has a higher support than other methods and also has a highest correlation with products sales ranking.