Empirical analysis of individual popularity and activity on an online music service system

被引：46

作者：

Hu, Hai-Bo ^{[1
]}

Han, Ding-Yi ^{[2
]}

机构：

[1] Shanghai Jiao Tong Univ, Dept Automat, Complex Networks & Control Lab, Shanghai 200240, Peoples R China

[2] Shanghai Jiao Tong Univ, Dept Comp Sci & Engn, Apex Data & Knowledge Management Lab, Shanghai 200240, Peoples R China

来源：

PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS | 2008年 / 387卷 / 23期

关键词：

popularity; activity; collective behavior; human dynamics;

D O I：

10.1016/j.physa.2008.06.018

中图分类号：

O4 [物理学];

学科分类号：

0702 ;

摘要：

Quantitative understanding of human behaviors supplies basic comprehension of the dynamics of many socio-economic systems. Based on the log data of an online music service system, we investigate the statistical characteristics of individual activity and popularity, and find that the distributions of both of them follow a stretched exponential form which interpolates between exponential and power law distribution. We also study the human dynamics on the online system and find that the distribution of interevent time between two consecutive listenings of music shows the fat tail feature. Besides, with the reduction of user activity the fat tail becomes more and more irregular, indicating different behavior patterns for users with diverse activities. The research results may shed some light on the in-depth understanding of collective behaviors in socio-economic systems. (C) 2008 Elsevier B.V. All rights reserved.

引用

页码：5916 / 5921

页数：6

共 30 条

[1]

ADLER M, 1985, AM ECON REV, V75, P208

[2] Toward the next generation of recommender systems: A survey of the state-of-the-art and possible extensions [J].