领域知识聚类性的动态演化分析
|
摘要
[目的/意义]探索领域知识发展过程中的聚类演化问题有助于揭示知识聚类的特征和规律,对于掌握知识生长演进过程中关联知识的聚集具有重要意义。[方法/过程]以复杂网络的思想为基础,基于标签邻接关系的发生值构建时间序列领域知识网络。即依据网络模体的理论,采用网络聚类系数的分析方法,对领域知识网络进行动态跟踪与分析;结合网络密度、特征路径长度、节点度值、封闭三元组等指标,从随机因素、度相关性、邻近关联3个方面对领域知识发展过程中的聚类演化现象进行分析。[结果/结论]研究结果表明:(1)领域知识在发展进程中始终保持较高的聚类性;(2)领域知识的聚类性同时包含随机性与结构性(非随机性)两方面因素;(3)领域知识聚类的动态状态在小世界网络和无标度网络之间摇摆演化;(4)领域知识的聚类状态在网络全局和局部节点之间表现出一定的差异性。
[Purpose/significance] Exploring the clustering evolution in the process of domain knowledge development can help to reveal the characteristics and rules of knowledge clustering,this is great significance to master the clustering rules of correlation knowledge in the development and evolution process. [Method/process] Based on the idea of complex network,this paper constructed the time series domain knowledge networks in accordance with the occurred-value of tags adjacency relation. That is,according to the network motif theory,this paper dynamically tracked and analyzed the domain knowledge networks by the analysis method of network clustering coefficient. Then,by combining with the network density,the characteristic path length,the node degree value,the triadic closure and other indicators,this article analyzed the clustering evolution in the process of domain knowledge development from random factors,degree correlation,and adjacent correlation. [Result/conclusion]The results show:(1)Domain knowledge in the development process always keeps a higher clustering.(2)The clustering of domain knowledge includes both randomness and structuration( non-randomness).(3)The dynamic status of domain knowledge clustering evolves between small-world network and scale-free network waveringly.(4)The clustering status of domain knowledge shows a certain difference between the whole network and local nodes.
[Purpose/significance] Exploring the clustering evolution in the process of domain knowledge development can help to reveal the characteristics and rules of knowledge clustering,this is great significance to master the clustering rules of correlation knowledge in the development and evolution process. [Method/process] Based on the idea of complex network,this paper constructed the time series domain knowledge networks in accordance with the occurred-value of tags adjacency relation. That is,according to the network motif theory,this paper dynamically tracked and analyzed the domain knowledge networks by the analysis method of network clustering coefficient. Then,by combining with the network density,the characteristic path length,the node degree value,the triadic closure and other indicators,this article analyzed the clustering evolution in the process of domain knowledge development from random factors,degree correlation,and adjacent correlation. [Result/conclusion]The results show:(1)Domain knowledge in the development process always keeps a higher clustering.(2)The clustering of domain knowledge includes both randomness and structuration( non-randomness).(3)The dynamic status of domain knowledge clustering evolves between small-world network and scale-free network waveringly.(4)The clustering status of domain knowledge shows a certain difference between the whole network and local nodes.
引文
[1]GARFIELD E.Citation indexes for science:a new dimension in documentation through association of ideas[J].Science,1955,122(3159):108-111.
[2]PRICE D J de S.Networks of scientific papers[J].Science,1965,149(3683):510-515.
[3]BARABASI A-L.Network science[M].Cambridge:Cambridge University Press,2016:20-41.
[4]SHIBATA N,KAJIKAWA Y,TAKEDA Y,et al.Comparative study on methods of detecting research fronts using different types of citation[J].Journal of the association for information science and technology,2009,60(3):571-580.
[5]李亚婷,马费成.基于标签共现的社会网络分析研究[J].情报杂志,2012,31(7):103-109.
[6]胡昌平,陈果.层次视角下概念知识网络的三元关系形态研究[J].图书情报工作,2014,58(4):11-16.
[7]NEWMAN M E J.Clustering and preferential attachment in growing networks[J].Physical review E,2001,64(2):025102.
[8]MAKANI J,SPITERI L.The dynamics of collaborative tagging:an analysis of tag vocabulary application in knowledge representation,discovery and retrieval[J].Journal of information&knowledge management,2010,9(2):93-103.
[9]LIU W,NANETTI A,CHEONG S A.Knowledge evolution in physics research:an analysis of bibliographic coupling networks[J].PLo S ONE,2017,12(9):e0184821.
[10]刘向,马费成,王晓光.知识网络的结构及过程模型[J].系统工程理论与实践,2013,33(7):1836-1844.
[11]滕广青.Folksonomy模式中紧密型领域知识群落动态演化研究[J].中国图书馆学报,2016,42(4):51-63.
[12]祝娜,王芳.基于主题关联的知识演化路径识别研究——以3D打印领域为例[J].图书情报工作,2016,60(5):101-109.
[13]MA J.The sustainability and stabilization of tag vocabulary in Cite ULike:an empirical study of collaborative tagging[J].Online information review,2012,36(5):655-674.
[14]MILO R,SHEN-ORR S,ITZKOVITZ S,et al.Network motifs:simple building blocks of complex networks[J].Science,2002,298(5594):824-827.
[15]NEWMAN M E J.网络科学引论[M].郭世泽,陈哲,译.北京:电子工业出版社,2014:126-130,152-173.
[16]BARABASI A-L,ALBERT R.Emergence of scaling in random networks[J].Science,1999,286(5439):509-512.
[17]滕广青,贺德方,彭洁,等.基于网络中心性的领域知识动态演化研究[J].图书情报工作,2016,60(14):128-134,141.
[18]MCGLOHON M,AKOGLU L,FALOUTSOS C.Statistical properties of social networks[C]//AGGARWAL C C.Social Network Data Analytics.New York:Springer,2011:17-39.
[19]滕广青,常志远,刘雅姝,等.Folksonomy知识组织模式中领域知识动态演化规律研究[J].图书与情报,2016(4):96-101,82.
[20]WATTS D J,STROGATZ S H.Collective dynamics of‘smallworld’networks[J].Nature,1998,393(6684):440-442.
[21]LEWIS T G.网络科学:原理与应用[M].陈向阳,巨修练,等,译.北京:机械工业出版社,2011:138-140.
[22]FRONCZAK A,HOLYST J A,JEDYNAK M,et al.Higher order clustering coefficients in Barabási-Albert networks[J].Physica A:statistical mechanics and its applications,2002,316(1):688-694.
[2]PRICE D J de S.Networks of scientific papers[J].Science,1965,149(3683):510-515.
[3]BARABASI A-L.Network science[M].Cambridge:Cambridge University Press,2016:20-41.
[4]SHIBATA N,KAJIKAWA Y,TAKEDA Y,et al.Comparative study on methods of detecting research fronts using different types of citation[J].Journal of the association for information science and technology,2009,60(3):571-580.
[5]李亚婷,马费成.基于标签共现的社会网络分析研究[J].情报杂志,2012,31(7):103-109.
[6]胡昌平,陈果.层次视角下概念知识网络的三元关系形态研究[J].图书情报工作,2014,58(4):11-16.
[7]NEWMAN M E J.Clustering and preferential attachment in growing networks[J].Physical review E,2001,64(2):025102.
[8]MAKANI J,SPITERI L.The dynamics of collaborative tagging:an analysis of tag vocabulary application in knowledge representation,discovery and retrieval[J].Journal of information&knowledge management,2010,9(2):93-103.
[9]LIU W,NANETTI A,CHEONG S A.Knowledge evolution in physics research:an analysis of bibliographic coupling networks[J].PLo S ONE,2017,12(9):e0184821.
[10]刘向,马费成,王晓光.知识网络的结构及过程模型[J].系统工程理论与实践,2013,33(7):1836-1844.
[11]滕广青.Folksonomy模式中紧密型领域知识群落动态演化研究[J].中国图书馆学报,2016,42(4):51-63.
[12]祝娜,王芳.基于主题关联的知识演化路径识别研究——以3D打印领域为例[J].图书情报工作,2016,60(5):101-109.
[13]MA J.The sustainability and stabilization of tag vocabulary in Cite ULike:an empirical study of collaborative tagging[J].Online information review,2012,36(5):655-674.
[14]MILO R,SHEN-ORR S,ITZKOVITZ S,et al.Network motifs:simple building blocks of complex networks[J].Science,2002,298(5594):824-827.
[15]NEWMAN M E J.网络科学引论[M].郭世泽,陈哲,译.北京:电子工业出版社,2014:126-130,152-173.
[16]BARABASI A-L,ALBERT R.Emergence of scaling in random networks[J].Science,1999,286(5439):509-512.
[17]滕广青,贺德方,彭洁,等.基于网络中心性的领域知识动态演化研究[J].图书情报工作,2016,60(14):128-134,141.
[18]MCGLOHON M,AKOGLU L,FALOUTSOS C.Statistical properties of social networks[C]//AGGARWAL C C.Social Network Data Analytics.New York:Springer,2011:17-39.
[19]滕广青,常志远,刘雅姝,等.Folksonomy知识组织模式中领域知识动态演化规律研究[J].图书与情报,2016(4):96-101,82.
[20]WATTS D J,STROGATZ S H.Collective dynamics of‘smallworld’networks[J].Nature,1998,393(6684):440-442.
[21]LEWIS T G.网络科学:原理与应用[M].陈向阳,巨修练,等,译.北京:机械工业出版社,2011:138-140.
[22]FRONCZAK A,HOLYST J A,JEDYNAK M,et al.Higher order clustering coefficients in Barabási-Albert networks[J].Physica A:statistical mechanics and its applications,2002,316(1):688-694.