期刊文献+

基于用户交互模型的会员网站每日活跃用户量分析 被引量:1

Analysis of daily active user in membership-based websites based on user interaction model
下载PDF
导出
摘要 现有的网站往往向注册用户提供服务,而网站中的每日活跃用户量往往决定着网站建设的成败。为了描述网站中每日活跃用户的动态变化,将用户在网站上的交互行为分为响应、扩散和衰落三种类型,并提出了一种基于用户交互模型的每日活跃用户量模型。通过响应、扩散和衰落三种交互行为的定义,进一步推导出每日活跃用户随着时间的变化率。通过对每日活跃用户随着时间的变化率进行分析得到如下结论:当网站中用户的响应概率小于衰落概率时网站的活跃用户将趋向于0,反之活跃用户趋于某个固定的常数。大量的真实数据实验表明,不论网站自身的运营是否成功,提出的方法都可以很好地描述网站的每日活跃用户数量及其发展趋势,这对于网站的建设和维护具有重要的指导意义。 Current websites usually provide services only for registered users, and the number of daily active user in each website decides whether the website will succeed. In order to describe the dynamics of daily active users in websites, this pa- per divided actions between users in a website into reaction, diffusion and decay, and proposed a user interaction based daily active user model. According to the definitions of reaction, diffusion and decay, it further inferred the rate of change of daily active users to time. While analyzing the rate of change of daily active users to time, it concluded that the number of daily ac- tive users would asymptotically tend to be a constant, and even zero while the rate of reaction was less than the rate of decay. Massive real dataset experiments show that, no matter whether the website itself is succeeded or not, the proposed approach can effectively describe the number of daily active users and its trend, and then can provide guidelines for building and main- taining of websites.
出处 《计算机应用研究》 CSCD 北大核心 2016年第8期2335-2338,共4页 Application Research of Computers
基金 国家自然科学基金资助项目(714211454) 山东省教育厅基金资助项目(2013A1234)
关键词 每日活跃用户 会员网站 用户交互模型 daily active user(DAU) membership based website user interaction model
  • 相关文献

参考文献17

  • 1Jin E M, Girvan M, Newman M E J. The structure of growing social networks[J]. Physical Review E,2001,64(4) :46-72. 被引量:1
  • 2Backstrom L, Huttenlocher D, Kleinberg J, et al. Group formation in large social networks : membership, growth, and evolution [ C ]//Proc of the 12th ACM SIGKDD Internatianal Conference on Knowledge Discovery and Data Mining. New York : ACM Press ,2006:44-54. 被引量:1
  • 3Leskovec J, Backstrom L, Kumar R, et al. Microscopic evolution of social networks [ C ]//Proc of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM Press,2008:462-470. 被引量:1
  • 4Kumar R, Novak J, Tomkins A. eial networks [ M ]//Link Mining tions. New York : Springer,2010 Structure and evolution of online so- Models, Algorithms, and Applica- 337- 357. 被引量:1
  • 5崔爱香,傅彦,尚明生,陈端兵,周涛.复杂网络局部结构的涌现:共同邻居驱动网络演化[J].物理学报,2011,60(3):803-808. 被引量:23
  • 6Kairam S, Wang D J, Leskovec J. The life and death of online groups: predicting group growth and longevity [ C ]//Proc of the 5th ACM International Conference on Web Search and Data Mining. New York : ACM Press,2012:673-682. 被引量:1
  • 7陈江宁,陆余良,郭浩.基于时间线数据的微博活跃用户数估计[J].计算机应用与软件,2013,30(8):246-249. 被引量:6
  • 8Cauwels P, Sornette D. Quis pendit ipsa pretia: facebook valuation and diagnostic of a bubble based on nonlinear demographic dynamics [J]. The doumal of Portfolio Management,2012,38(2):56-66. 被引量:1
  • 9Boyd D. White flight in networked publics? How race and class shaped American teen engagement with myspace and facebook [ M ]. 2013 : 203- 220. 被引量:1
  • 10Facebook Inc. Facebook reports second quarter 2013 results [ EB/ OL]. (2015). http://investor, lb. com/releasedetail, cfm? Relea- seID = 780093. 被引量:1

二级参考文献43

共引文献35

同被引文献4

引证文献1

二级引证文献4

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部