用户—产品二部分网络中用户声誉实证研究

Empirical Analysis of the User Reputation in User′s Object Bipartite Networks

用户声誉度量用户评分的准确程度,用户声誉的研究对于保障社会经济和民生的健康发展具有重要意义。在电影网站MovieLens数据上从用户活跃度与记忆性两个角度进行用户声誉的实证研究。根据用户的度分组,发现用户声誉随着用户度的增加而增加,将数据集按照时间分成36个季度的片段,同样发现随着用户度的增加,用户声誉出现上升的趋势。同时,将数据集按照时间分成9个年度的片段,发现用户的持续存在率逐年减小,提出一种度量指标来衡量用户声誉记忆性,发现5年之内用户声誉排名的肯德尔系数比用户度的肯德尔系数更高,表明用户声誉比用户活跃度更具有记忆性。通过建立随机模型与实证结果进行比较,发现真实数据集上用户声誉与度的关系以及声誉的记忆性与随机模型有显著不同。

User reputation measures user′s ability of rating accurate assessments of various objects,and is of great significance for ensuring the healthy development of social economy and people's livelihood.This paper empirically analyzed the user′s reputationin the MovieLens data setfrom two aspects of user′s activity and rating memory.Grouping by the user′s degree,the results showed that the user′s reputation increases with the user′s degree.When the data set was divided into 36 quarters according to the time,it was also found that the user′s reputation presents rising trend with the increase of the user′s degree.Moreover,the data set was divided into 9 years according to time,the results showed that the user's persistence rate is gradually reduced year by year.Furthermore,it presented a metric to measure the memory of user reputation.The results showed that the Kendall coefficients of user′s reputation ranking in 5 years are higher than those of user′s degree,indicating that the user′s reputation presents more memory than user′s activity.In addition,it proposed a null model to be compared with the empirical results.The results showed that the relationship between user′s reputation and degree as well as the memory of user reputation on the empirical data are significantly different from those of the null model.