知识扩散路径上节点的分类和聚类分析——以知识分享平台“知乎”数据为例
|
摘要
【目的/意义】研究知识扩散路径和知识扩散网络中节点的特征,从而服务于知识扩散的模型研究。【方法/过程】通过对流行的中文知识分享平台-"知乎"网络上一次典型的知识扩散进行回溯,建立参与知识扩散的节点的知识扩散网络和节点之间的社会关系网络。通过对节点历史行为和网络位置属性的交叉分类,分析整个知识扩散网络中节点的统计特征。并且,对社会关系网络中一个节点的所有相邻节点进行K-Means聚类,分析这些相邻节点的特征。【结果/结论】通过分析,发现了知识扩散过程中,节点较强的聚类特性。更重要的是,父节点在知识扩散网络中的子节点同时具有较强的聚类特征,并与父节点具有较强的相似性。这些通过交叉分析挖掘得到的数据特征和结论,能够为知识扩散模型研究提供新的研究思路和方向。
【Purpose/significance】In order to better understand and model the knowledge diffusion process, this paper addresses characteristics and pattern of nodes on the diffusion paths and network.【Method/process】Through tracing back a typical knowledge diffusion paths from one of the most popular Chinese knowledge-sharing social media platform-"ZHIHU(知乎)"network, a knowledge diffusion network and related social network are represented. Briefly, two kinds of analysis are done: one is to mine the characteristics of nodes based on their label on both the knowledge diffusion network and the social network,the other is to cluster the out-linked nodes of the same node, the son nodes of a same father node in the social network named.【Result/conclusion】According to our cross-correlation analysis, the results of K-Means clustering of nodes on the knowledge diffusion paths are significant. More importantly, the son nodes of a same father node show great similarity and cluster well. These results imply a novel research direction for modeling the real knowledge diffusion process.
【Purpose/significance】In order to better understand and model the knowledge diffusion process, this paper addresses characteristics and pattern of nodes on the diffusion paths and network.【Method/process】Through tracing back a typical knowledge diffusion paths from one of the most popular Chinese knowledge-sharing social media platform-"ZHIHU(知乎)"network, a knowledge diffusion network and related social network are represented. Briefly, two kinds of analysis are done: one is to mine the characteristics of nodes based on their label on both the knowledge diffusion network and the social network,the other is to cluster the out-linked nodes of the same node, the son nodes of a same father node in the social network named.【Result/conclusion】According to our cross-correlation analysis, the results of K-Means clustering of nodes on the knowledge diffusion paths are significant. More importantly, the son nodes of a same father node show great similarity and cluster well. These results imply a novel research direction for modeling the real knowledge diffusion process.
引文
1 Nekovee M,Moreno Y,Bianconi G,Marsili M.Theory of Rumour Spreading in Complex Social Networks[J].Physica A,2007,(374):457-470.
2 Domenico MD,Lima A,Mougel P,and Musolesi M.The Anatomy of a Scientific Rumor[J].Scientific Reports,2013,(3):2980.
3 Li F,Du TC.Listen to me-evaluating the influence of micro-blog[J].Decision Support Systems,2014,(62):119-130.
4 Bass F M.Product Growth for Model Consumer Durables[J].Management Science,1969,15(5):215-227.
5 魏莹,李锋.知识分享型网络的网络演化及知识扩散模型研究[J].情报科学,2018,36(4):123-129.
6 陈柏彤,张斌.产业集群知识扩散动态演化分析[J].情报科学,2016,34(9):150-154.
7 党永杰,邱均平,郑世珏.基于改进BA模型的作者合作加权网络动态演化研究[J].情报学报,2017,36(1):28-38.
8 李纲,巴志超.科研合作超网络下的知识扩散演化模型研究[J].情报学报,2017,36(3):274-284.
9 巴志超,李纲,朱世伟.基于知识超网络的科研合作实证研究和建模[J].情报学报,2016,35(6):630-639.
10 刘璇,李嘉,陈智高,张朋柱,范静.科研创新网络中知识扩散演化机制研究[J].科研管理,2015,36(7):19-27.
11 Leskovec J,Kleinberg J,Faloutsos C.Graphs over Time:Densification Laws,Shrinking Diameters and Possible Explanations[C]//In Proceedings of ACM SIGKDD International Conference on Knowledge Discovery and Data Mining,2005:177-187.
12 陈泽明,杨敏,何山.三维空间对企业内生创新的知识流溢出机理及其实证研究-基于开放创新视角[J].软科学,2016,30(1):9-13.
13 周文,陈伟,郎益夫.集群创新网络知识动态增长研究:基于过程视角[J].系统工程学报,2015,30(4):431-441.
14 张丽芳,张福进,尚洁.知识扩散、集群创新与集群网络的扩张-基于物联网产业的研究[J].软科学,2014,28(10):11-17.
15 魏莹,刘冠,李锋.线上社交网络上信息扩散中“隐形”关键节点的识别及影响力评价[J].情报科学,2018,36(3):138-143.
16 Wang R,Wang Z.Consumer Choice Models with Endogenous Network Effects[J].Management Science,2017,63(11):3944-3960.
17 Ma L,Krishnan R,Montgomery AL.Latent Homophily or Social Influence?An Empirical Analysis of Purchase Within a Social Network[J].Management Science,2015,61(2):454-473.
18 路燕,于晓东.基于改进K-Means算法的企业竞争情报研究—以社会网络分析为方法[J].情报科学,2017,35(12):81-85.
2 Domenico MD,Lima A,Mougel P,and Musolesi M.The Anatomy of a Scientific Rumor[J].Scientific Reports,2013,(3):2980.
3 Li F,Du TC.Listen to me-evaluating the influence of micro-blog[J].Decision Support Systems,2014,(62):119-130.
4 Bass F M.Product Growth for Model Consumer Durables[J].Management Science,1969,15(5):215-227.
5 魏莹,李锋.知识分享型网络的网络演化及知识扩散模型研究[J].情报科学,2018,36(4):123-129.
6 陈柏彤,张斌.产业集群知识扩散动态演化分析[J].情报科学,2016,34(9):150-154.
7 党永杰,邱均平,郑世珏.基于改进BA模型的作者合作加权网络动态演化研究[J].情报学报,2017,36(1):28-38.
8 李纲,巴志超.科研合作超网络下的知识扩散演化模型研究[J].情报学报,2017,36(3):274-284.
9 巴志超,李纲,朱世伟.基于知识超网络的科研合作实证研究和建模[J].情报学报,2016,35(6):630-639.
10 刘璇,李嘉,陈智高,张朋柱,范静.科研创新网络中知识扩散演化机制研究[J].科研管理,2015,36(7):19-27.
11 Leskovec J,Kleinberg J,Faloutsos C.Graphs over Time:Densification Laws,Shrinking Diameters and Possible Explanations[C]//In Proceedings of ACM SIGKDD International Conference on Knowledge Discovery and Data Mining,2005:177-187.
12 陈泽明,杨敏,何山.三维空间对企业内生创新的知识流溢出机理及其实证研究-基于开放创新视角[J].软科学,2016,30(1):9-13.
13 周文,陈伟,郎益夫.集群创新网络知识动态增长研究:基于过程视角[J].系统工程学报,2015,30(4):431-441.
14 张丽芳,张福进,尚洁.知识扩散、集群创新与集群网络的扩张-基于物联网产业的研究[J].软科学,2014,28(10):11-17.
15 魏莹,刘冠,李锋.线上社交网络上信息扩散中“隐形”关键节点的识别及影响力评价[J].情报科学,2018,36(3):138-143.
16 Wang R,Wang Z.Consumer Choice Models with Endogenous Network Effects[J].Management Science,2017,63(11):3944-3960.
17 Ma L,Krishnan R,Montgomery AL.Latent Homophily or Social Influence?An Empirical Analysis of Purchase Within a Social Network[J].Management Science,2015,61(2):454-473.
18 路燕,于晓东.基于改进K-Means算法的企业竞争情报研究—以社会网络分析为方法[J].情报科学,2017,35(12):81-85.