...
【24h】

Selection bias may influence social network data

机译:选择偏见可能会影响社交网络数据

获取原文
获取原文并翻译 | 示例
           

摘要

Analyzing electronic social network data may help researchers develop and test theories of social interaction. Previous research that examined the propagation of chain letters across the Internet found network patterns that appeared to be inconsistent with classical models. Benjamin Golub and Matthew Jackson (pp. 10833-10836) report that chain letter propagation can be accurately described by adjusting the classical Galton-Watson model for selection bias in the data. The Galton-Watson model treats information propagation as a family tree in which each sender independently produces a random number of "offspring." The researchers applied the Galton-Watson model to chain letter distribution and found that the model reproduced branching patterns similar to the chain letter data, but only when the model was weighted more heavily toward extensive letter dissemination.
机译:分析电子社交网络数据可能有助于研究人员开发和测试社交互动理论。以前的研究检查了连锁字母在Internet上的传播,发现与经典模型不一致的网络模式。本杰明·古鲁布(Benjamin Golub)和马修·杰克逊(Matthew Jackson)(第10833-10836页)报告说,通过调整数据中选择偏倚的经典高尔顿-沃森模型,可以准确地描述连锁字母的传播。 Galton-Watson模型将信息传播视为家谱,其中每个发送者独立产生随机数量的“后代”。研究人员将Galton-Watson模型应用于连锁信分布,发现该模型复制的分支模式与连锁信数据相似,但仅当该模型的权重偏重于广泛的字母传播时才如此。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号