校园网络信息传播特性与用户影响力研究
|
摘要
随着互联网技术的发展和网络应用的广泛普及，互联网已经成为人们分享和传播信息的重要场所，网络交互行为已经成为社会生活的一种重要的交互方式和信息传播渠道。特别是对于广大的高校大学生而言，校园网络已经成为其工作和生活最为重要的手段和途径之一。然而，互联网信息在高校大学生之间进行传播的规律以及信息交互的本质特征还没有形成规律和清晰的认识。个体用户在信息传播过程中所起到的作用还无法精确的分析和度量。在这种背景下，研究校园用户的网络行为特性，并在此基础上通过实测数据分析网络信息的传播过程和用户信息分享行为之间的关系已经成为信息科学、社会科学、传播学等交叉学科领域的研究热点。本文从校园网络信息传播结构出发，深入研究网络拓扑结构对于信息传播的影响及其规律性。主要是针对当前校园网络中最主要的新媒体网络传播渠道：校园论坛、社交网络以及微博客，三种最典型的在线社会网络平台进行网络结构以及信息传播过程的测量和分析。研究网络用户行为特征，并在此基础上对网络用户影响力进行分析和建模。并通过针对三种典型媒体网络形态特点，提出针对性的用户影响力评估算法，度量用户在网络信息传播中的重要程度。本文的研究有助于认识互联网信息交互和传播的基本模式和特点，对理解互联网环境中和现实社会中人类的复杂群体行为也有着重要意义。
论文的主要研究工作和创新点有以下方面：
1.对于校内网络论坛网络结构进行深入的测量和分析，提出了基于有向权重网络模型来构建论坛人际关系网络结构，准确的表现用户之间的互动关系。通过对实测数据的深入分析，实际测量了网络的无标度（Scale-free）和小世界（Small-world）性质，发现网络呈现自发组织性，并且少量核心用户节点左右了整个网络社区的言论，这为意见领袖的存在的社会性根源进行了数值刻画。在此基础上提出了一种基于用户兴趣和回帖内容情感性分析的LeaderRank算法来进行意见领袖权威度的评估，通过对比主流的意见领袖识别算法，发现网络结构和文本语义分析可以有效的提高对意见领袖的识别准确率，最后对意见领袖和论坛版块的关系进行深入分析后，发现核心用户实际上总是活跃在少量的重要版块上。
2.以人人网为例，深入分析了社交网络信息传播机制，将信息传播过程分为从校外到校内，以及校内用户之间传播过程并建立了相应的交联网络用户模型和有效传播路径模型。该模型最大的创新在于可以从微观角度清晰的看出信息在信息传播渗透到校园内，以及校园内信息是如何扩散的。通过实测数据统计发现：并不存在一个相对集中的向校内用户进行信息渗透的校外用户群落，但是校外信息传播到校内的第一接触点是非常少的一部分人群，发现如果缺少这些少数核心人群参与信息传播，外界信息就难以在校园内进行扩散。同时信息在校园内二次传播过程中存在少量的核心节点，这些节点对信息传播也起到了核心的推动作用。于是本文进一步提出了用户传播影响力评估InfluenceRank算法，综合考虑个体传播意愿和社会传播能力这两个因素，定量的对每个个体的传播影响力进行度量，并通过与用户访问量这样的社会性指标进行对比，验证了算法的准确性。
3.以新浪微博为例，深入分析了微博信息传播机制，构建了两种信息分享网络模型——用户收听网络模型和信息转发网络模型，其中信息转发模型最大的创新在于是基于真实信息转发路径的用户间行为的抽象，能够直观的反映用户之间信息传播的真实情况。在两个传播模型的基础上，通过网络测量的手段获取到某高校的所有微博访问实际数据，通过进行深入的统计和社会网络分析，发现校园用户具有非常强烈的聚集性和乐于分享、善于原创的特性，对信息传播而言，得出少量的部分用户占据了绝大多数的信息传播行为的结论。此外，本文充分考虑了弱连带人际关系网络中信息传播的特点，提出核心辐射网络模型，并且充分考虑了用户之间互动的亲近性，提出了WeiboRank算法，它能对用户的真实传播影响力进行精确定量评估。实证结果表明，本文提出的WeiboRank算法能更准确的对用户的信息传播能力进行评估，无论是在识别准确性和计算效率上，整体上都明显优于对比算法。
With the development of Internet technology and a wide range of popular networkapplications, Internet has become the most important place of information sharing anddiffusion, computer based Internet interactions behavior has become an important mode ofuser communication and information dissemination channels.Especially for the majority ofcollege students, the campus network has become an indispensable part of life andwork.However, the essential characteristics of the Internet information diffusion andexchange have not formed a clear and profound understanding.Individual users in theinformation dissemination process of the role of analysis and can not accurately measure.Inthis context, the study of behavioral characteristics of the campus network users, andanalysis on the basis of the measured data through the network of informationdissemination process and user behavior information sharing between a cross-disciplinaryresearch focus.In this paper, information dissemination structure to the campus network,research network topology for the information dissemination and its regularity.Mainly forthe current main campus network in new media network communication channels: forums,social networking and micro-blog the three most typical online social networking platformfor network infrastructure, and information dissemination process of measurement andanalysis.Research internet user behavior, construct model of the network users impact,proposed algorithm to value user impaction, measure the importance of user in informationdissemination process. The research of the paper can help people to understand the networkinfrastructure of information diffusion process and basic characteristic and the complexhuman group behavior has important implications.
The main thesis research and innovation in the following areas:
1. We measure and analysis the network structure of the campus BBS, proposed aweighted network model to construct the user relationship in the bbs network. Throughin-depth analysis of the measured data, the BBS network has the character of scale-free andsmall world, showing that the network self-organization, and a small amount of core usercontrol of the network nodes of speech community.tell us the causes of the existence of theopinion leaders.Then we proposed a algorithm to assess the degree of the user authoritynamed LeaderRank, which is based analysis of emotional replies of the user. By thecompare the main opinion leader recognition algorithms, we found that the networkarchitecture can effectively help the identification of th opinion leaders. At last we analysis the relationship of the core user and the BBS broad and found that the most active useralways on a small number of BBS broad.
2. We research the websit of renren as an example,analysis of the social networkinformation dissemination mechanism, the informaion diddemination process is divided totwo process,from outside to inside, and campus communication process between usersandestablishment of the corresponding cross-linked network user model and effectivepropagation path modell.The biggest innovation of the model is that it can be clearly seenfrom the microscopic point of information dissemination of information to infiltrate thecampus, and how the information is spread within the campus.Statistics found bymeasuring the relative concentration and there is not a fixed penetration of information tothe campus user community of external users, but the dissemination of information tocampus outside the first point of contact is a very small part of the crowd, so long as thecontrol of a small number of core internal users, external information is difficult to spreadon campus.So we proposed a spread of the influence of the user evaluation algorithm,considering the spread of individual will and social communication capacities of these twofactors, and through comparison such social indicators the amount of user visit, valid theaccuracy of the algorithm.
3. By the analysis of the mechanisms of the sina microblog informaion dissemination,we build two informaition-sharing network models: user listening network model and usersharing network model. The innovation of the user sharing network model is theinformation diffusion process based on real user behavior. We got the actual data of thecollege access the sina microblog. Based of the data statistics and analysis, we found thatcampus users have a very strong characteristic of aggregation and willing to shareinformation. In terms of information dissemination, a small part of the user account for thevast majority of information and communication behavior.Then an algorithm is alsoproposed based on the pagerank named WeiboRank algorithm can real assessment thespread of the influence of the user. The results show that algorithm presented in this paperWeiboRank accurate dissemination of information on the user's ability to assess whether theinformation in the user listening network or sharing network as a whole are significantlybetter than the comparison algorithms.
论文的主要研究工作和创新点有以下方面：
1.对于校内网络论坛网络结构进行深入的测量和分析，提出了基于有向权重网络模型来构建论坛人际关系网络结构，准确的表现用户之间的互动关系。通过对实测数据的深入分析，实际测量了网络的无标度（Scale-free）和小世界（Small-world）性质，发现网络呈现自发组织性，并且少量核心用户节点左右了整个网络社区的言论，这为意见领袖的存在的社会性根源进行了数值刻画。在此基础上提出了一种基于用户兴趣和回帖内容情感性分析的LeaderRank算法来进行意见领袖权威度的评估，通过对比主流的意见领袖识别算法，发现网络结构和文本语义分析可以有效的提高对意见领袖的识别准确率，最后对意见领袖和论坛版块的关系进行深入分析后，发现核心用户实际上总是活跃在少量的重要版块上。
2.以人人网为例，深入分析了社交网络信息传播机制，将信息传播过程分为从校外到校内，以及校内用户之间传播过程并建立了相应的交联网络用户模型和有效传播路径模型。该模型最大的创新在于可以从微观角度清晰的看出信息在信息传播渗透到校园内，以及校园内信息是如何扩散的。通过实测数据统计发现：并不存在一个相对集中的向校内用户进行信息渗透的校外用户群落，但是校外信息传播到校内的第一接触点是非常少的一部分人群，发现如果缺少这些少数核心人群参与信息传播，外界信息就难以在校园内进行扩散。同时信息在校园内二次传播过程中存在少量的核心节点，这些节点对信息传播也起到了核心的推动作用。于是本文进一步提出了用户传播影响力评估InfluenceRank算法，综合考虑个体传播意愿和社会传播能力这两个因素，定量的对每个个体的传播影响力进行度量，并通过与用户访问量这样的社会性指标进行对比，验证了算法的准确性。
3.以新浪微博为例，深入分析了微博信息传播机制，构建了两种信息分享网络模型——用户收听网络模型和信息转发网络模型，其中信息转发模型最大的创新在于是基于真实信息转发路径的用户间行为的抽象，能够直观的反映用户之间信息传播的真实情况。在两个传播模型的基础上，通过网络测量的手段获取到某高校的所有微博访问实际数据，通过进行深入的统计和社会网络分析，发现校园用户具有非常强烈的聚集性和乐于分享、善于原创的特性，对信息传播而言，得出少量的部分用户占据了绝大多数的信息传播行为的结论。此外，本文充分考虑了弱连带人际关系网络中信息传播的特点，提出核心辐射网络模型，并且充分考虑了用户之间互动的亲近性，提出了WeiboRank算法，它能对用户的真实传播影响力进行精确定量评估。实证结果表明，本文提出的WeiboRank算法能更准确的对用户的信息传播能力进行评估，无论是在识别准确性和计算效率上，整体上都明显优于对比算法。
With the development of Internet technology and a wide range of popular networkapplications, Internet has become the most important place of information sharing anddiffusion, computer based Internet interactions behavior has become an important mode ofuser communication and information dissemination channels.Especially for the majority ofcollege students, the campus network has become an indispensable part of life andwork.However, the essential characteristics of the Internet information diffusion andexchange have not formed a clear and profound understanding.Individual users in theinformation dissemination process of the role of analysis and can not accurately measure.Inthis context, the study of behavioral characteristics of the campus network users, andanalysis on the basis of the measured data through the network of informationdissemination process and user behavior information sharing between a cross-disciplinaryresearch focus.In this paper, information dissemination structure to the campus network,research network topology for the information dissemination and its regularity.Mainly forthe current main campus network in new media network communication channels: forums,social networking and micro-blog the three most typical online social networking platformfor network infrastructure, and information dissemination process of measurement andanalysis.Research internet user behavior, construct model of the network users impact,proposed algorithm to value user impaction, measure the importance of user in informationdissemination process. The research of the paper can help people to understand the networkinfrastructure of information diffusion process and basic characteristic and the complexhuman group behavior has important implications.
The main thesis research and innovation in the following areas:
1. We measure and analysis the network structure of the campus BBS, proposed aweighted network model to construct the user relationship in the bbs network. Throughin-depth analysis of the measured data, the BBS network has the character of scale-free andsmall world, showing that the network self-organization, and a small amount of core usercontrol of the network nodes of speech community.tell us the causes of the existence of theopinion leaders.Then we proposed a algorithm to assess the degree of the user authoritynamed LeaderRank, which is based analysis of emotional replies of the user. By thecompare the main opinion leader recognition algorithms, we found that the networkarchitecture can effectively help the identification of th opinion leaders. At last we analysis the relationship of the core user and the BBS broad and found that the most active useralways on a small number of BBS broad.
2. We research the websit of renren as an example,analysis of the social networkinformation dissemination mechanism, the informaion diddemination process is divided totwo process,from outside to inside, and campus communication process between usersandestablishment of the corresponding cross-linked network user model and effectivepropagation path modell.The biggest innovation of the model is that it can be clearly seenfrom the microscopic point of information dissemination of information to infiltrate thecampus, and how the information is spread within the campus.Statistics found bymeasuring the relative concentration and there is not a fixed penetration of information tothe campus user community of external users, but the dissemination of information tocampus outside the first point of contact is a very small part of the crowd, so long as thecontrol of a small number of core internal users, external information is difficult to spreadon campus.So we proposed a spread of the influence of the user evaluation algorithm,considering the spread of individual will and social communication capacities of these twofactors, and through comparison such social indicators the amount of user visit, valid theaccuracy of the algorithm.
3. By the analysis of the mechanisms of the sina microblog informaion dissemination,we build two informaition-sharing network models: user listening network model and usersharing network model. The innovation of the user sharing network model is theinformation diffusion process based on real user behavior. We got the actual data of thecollege access the sina microblog. Based of the data statistics and analysis, we found thatcampus users have a very strong characteristic of aggregation and willing to shareinformation. In terms of information dissemination, a small part of the user account for thevast majority of information and communication behavior.Then an algorithm is alsoproposed based on the pagerank named WeiboRank algorithm can real assessment thespread of the influence of the user. The results show that algorithm presented in this paperWeiboRank accurate dissemination of information on the user's ability to assess whether theinformation in the user listening network or sharing network as a whole are significantlybetter than the comparison algorithms.
引文
[1]中国互联网络信息中心,第28次中国互联网络发展状况统计报告.2011.7.19
[2]唐.泰普斯科特,数字化成长：网络时代的崛起.东北财经大学出版社,1999
[3]周荣旗,方冰. Web2.0网站传播的特性比较与趋势——以Gigg与Twitter为例.网络传播,2009.11, p.60-61
[4]张瑞.“校园SNS”火爆的学理思考.传媒观察,2007.2,p.53-59
[5]能向群. SNS网络人际传播的现实化回归.新闻传播.2006.9,p.23-28
[6]张宇,在线社会网络信任计算与挖掘分析中若干模型与算法研究.博士学位论文,浙江大学,2009
[7] Leskovec J, Horvitz E. Planetary-scale views on a large instant-messaging network,Proceedings of the17thInternational Conference on World Wide Web.2008, p.915-924
[8] Xu J, Chen H, Crimenet explorer: Aframework for criminal network knowledgediscovery, ACM Transactions on Information Systems,2005,23(2), p.201-226
[9] Kempe D, Kleinberg J, Influential nodes in a diffusion model for social networks,Proceeding of the32nd International Colloquium on Automata, Languages andProgramming,2005, p.1127-1138
[10]Richardson M, Domingos P. Mining knowledge-sharing sites for viral marketing, The8thACM SIGKDD International Conference on Knowledge Discovery and DataMining,2002
[11] Java A, Kolari P, et al. Modeling th spread of influence on the blogosphere,Proceeding of the15thInternational World Wide Web Conference,2006
[12]Hill S, Provost F, Network-based marketing: Identifying likely adopters via consumernetwork, Statistical Science,2006,21(2), p.256-276
[13]段志生.图论与复杂网络.力学发展,2008,38
[14]Watts D J, Strogatz SH, Collective dynamics of small-world networks,Nature,1998,393, p.440-442
[15]Jababaie A, Lin J, Morse A S, Coordination of groups of mobile anutomomous agentsusing nearest neighbor rules, IEEE Transactions on Automatic Control,2003,48,p.988-1001
[16]薛可,余明阳.人际传播学.上海同济大学出版社,2007,2
[17]N. T. J. Bailey, The Mathematical Theory of Infectious diseases and its applications,New York, hafner Press,1975
[18]R.M. Anderson and R. M. May. Infectiious diseases of humans, Oxford, OxfordUniversity Press,1991
[19]Meade N., Islam T. Modeling and forecasting the diffusion of innovation:a25-yearreview, International Journal of Rorecasting,2006.22(3), p.519-545
[20]S. Milgram. The Small World Problem. Psychology Today,1967,60~67
[21] R. Albert, A.-L. Barabasi. Statistical Mechanics of Complex Networks. Reviews of ModernPhysics,2002,74(1):47~97
[22]Newman M. E. J. The Structure and Function of Complex Networks. SIAM Review,2003,45:167~256
[23]Malarz K, Szvetelszky Z,et al. Theory of Rumour Spreading in Complex SocialNetworks, Physica A2007.374(1),p.457-470
[24]Solmon S, Weisbuch G.,et al. Soicial percolation model, Physica A,2000,277(1),p.237-247
[25]Han J, Kamber M. Data Mining: Concepts and Techniques, Morgan Kaufmann,2001
[26]Milgram S, The small world problem, Psychology Today,1967.2
[27]Gramovetter M, The Strength of Weak Ties, American Journal of Sociology,1973.78(6)
[28]Albert R, Jeong H and Barabasi A, The Diameter of the World Wide Web, Nature,1999.401, p.130-137
[29]Newman M, The Structure of Scientific Collaboration Networks, Proceedings of theNational Academy of sciences,2001,p.409-415
[30]Amaral L, Scala A, Classes of Small-world Networks, Proceedings of the NationalAcademy of Sciences,2000, p.149-152
[31]Adamic L, Buyukkokten O, Asocial Networks Caught in the Web, First Monday,2003,8(6)
[32]Mislove A, Marcon M. Measurement and Analysis of Online SocialNetworks,Proceeding of the7th ACM SIGCOMM conference on InternetMeasurement,USA2007, p.29-42
[33]Ahn YY, Han S, Keak H, Analysis of topological characteristics of huge online socialnetworking Services, Proceedings of the16thinternatiaonal conference on World WideWeb,USA,2007, p.835-844
[34]Fu F,Liu L, Yan K, The structure of self-organized blogosphere, Physica,2006
[35]Backstrom L, Kumar R, Preferential behavior in online groups, WSDM’08,2008,.p117-128
[36]Girvab N, Newman J, Community structure in social and bilolgical networks,PNAS,2002,p7821-7826
[37]Barabasi A, Albert R, Emergence of Scaling in Ramdom Networks, Science,1999,p.9509-512
[38]Ramasco J, Dorogovtsec S, Self-organization of collaboration networks, Physica,2004.70, p.1-10
[39]Shi D H, Chen Q H, Markov Chain-based Numerical Method for Degree Distributionsfo Growing Networks, Physical,2005,71,p.36-140
[40]方锦清,毕桥,李永.复杂动态网络的一种和谐统一的混合择优模型及其普适特性.中国科学G期,2007,37, p.230-248
[41]章忠志.复杂网络的演化模型研究,博士学位论文,大连理工大学,2006
[42]Wan XJ. Yang JW. Learning information diffusion process on the web, Proceedings ofthe16thinternational conference on World Wide Web,2007,1173-1174
[43]Daniel G., R. Guha, Information diffusion throuth blogspace, Proceedings of the13thinternational World wide Web Conference, p.491-501
[44]Jure Leskovec, Mary M., Christos F., Cascading behavior in large blog graphs, SIAMInternational conference on data mining,2007
[45]Nazir A., Raza S., Unveiling facebook: a measurement study of social network basedapplications. In Proc. ACM IMC2008
[46]Nazir A., Raza S., et al, Network-level footprints of facebook applications, ACM IMC2009
[47]Fabian S., Anja F.,et al, Understanding online social network usage from a networkperspective, IMC2009, p.35-48
[48]Acquisti A., Gross R., Imagined communities: awareness, information sharing andprivacy on the Facebook. In Privacy enhancing technologies,2006
[49]Stutzman F., An evaluation of identity sharing behavior in social network communities,iDMAa Journal,2006
[50]Baker W, Faulkner R, The social organization of conspiracy, Illegal networks in theheavy electrical equipment industry, American Sociological Review,1993,58(6),p.837-860
[51]Bollen J,De Sompel, et al, Toward alternative metrics of journal impact: A comparisonof download and citation data, Information Processing&Management,2005,41(6),p.1419-1440
[52]Evertt M, Borgatti S, The centrality of groups and classes, Journal of MathematicalSociology,1999,23(3),p.181-201
[53]Newman MJ, Who is the best connected scientist? A study of scientific coauthorshipnetworks, Physical Review E,2001,64, p.337-370
[54]唐常杰,温粉莲,乔少杰.基于社会网络最短路径挖掘犯罪集团核心.计算机科学,2006,33（11）, p.23-31
[55]Page L, sergey Brin, The pagerank citation ranking: Bring order to the web, StanfordUniversity,1998
[56]Kleinberg J M, Hubs, authorities, and communities, ACM Computing surveys,1999,31
[57]Liu X, Bollen J,Nelson M,et al, Co-authorship networks in the digital library researchcommunity, Electronic commerce research and applications,2005,41, p.1462-1480
[58]Zhang J, Ackerman M S, Expertise networks in online communities: Structure andalgorithms, Proceeding of the16thInternational World Wide Web Conference,2007
[59]Peltomaki M, Alava M, Correlations in bipartite collaboration networks, Journal ofStatistical Mechanics: Theory and Experiment,2006
[60]彭小川,毛晓丹. BBS群体特征社会网络分析,青年研究.2004,4,p.39-44
[61]Peng Xiaochuan, Mao Xiaodan.Social Network analysis of BBS communitycharacteristics[J],Youth Studies,2004,4,p.39-44
[62]R.Albert, A.L.Barabasi, Statistical Mechanics of Complex Networks, Rev. Mod. Phys.2002,74, p.47-97.
[63]S.N.Dorogovtsev, J.F.F.Mendes, Evloution of networks, Adv. Phys.2002,51,p.1079-1187
[64]N.Matsumura. Y.Ohsawa. Ming and Characterizing Opinion Leaders from ThreadedOnline Discussions[J],KES2007
[65]K.-I.Goh,Y.-h.Eom, Structure and evolution of online social relationship:Heterogeneity in unrestricted discussions[J], Physical Review,2006,E73,p.066-123
[66]Zhongbao, K., Z. Changshui. Repay networks on a bulletion board system[J]. PhysicalReview E,2003,67(3),p.036-117
[67]宫辉,徐渝.高校BBS社群结构与信息传播的影响因素.西安交通大学学报,2007,27(1),p.93-96
[68]Zhang, J., M. Ackerman, and L. Adamic. Expertise networks in online communities:structure and algorithms [J]. WWW '07.2007
[69]Zhai Zhongwu, Xu Hua. Identifying opinion leaders in BBS[J], IEEE Proceedings ofWeb Intelligence and Intelligent Agent Technology,2008
[70]Barrat A,Barthelemy M, Vespingani A., Statistical Mechanics of Complex Networks,Physical Review Letters,2004,p.47-97
[71]D.J.Watts, S.H.Strogalz. Collective dynamics of small-world networks, Nature393,1998,p.440-442
[72]Hengmin zhou, Daniel Zeng, Finding leaders from opinion networks, IEEEInternational Conference on Digital Object Identifier,2009,p.266-268
[73]黄昌宁,赵海.中文分词十年回顾.中文信息学报,2007,21(3),p.8~19
[74]Newman M E, Girvan M. Finding and evaluating community structure in networks[J].Physical Review E,2004,69,p.26-39
[75]L. A. Matsunaga, N. F. F. Ebecken. Term Weighting Approaches for TextCategorization Improving[C]. in: ISDA'08, Eighth International Conference onIntelligent Systems Design and Applications,2008(1),p.409-414
[76]O. W. Kwon, J. H. Lee. Web Page Classification Based on k-Nearest NeighborApproach[C]. in: Proceedings of the5th International Workshop on InformationRetrieval with Asian Languages.2000,p.9-15
[77]A. Bergo. Text Categorization and Prototypes,the University of Amsterdam,2001
[78]苏金树,张博锋,徐昕.基于机器学习的文本分类技术研究进展.软件学报,2006,17(9), p.1848~1859
[79]T.M.Cover and PE.Hart, Rates of convergence for nearest neighbor procedure, inProc.HaWaii Int.Conf.onSystem Science.2009, p.214-223
[80]Shen yang, Shuchen li, ling zhen, Emotion mining research on micro-blog,SWS2009,p.71-75
[81]Ihab F. Ilyas, George Beskales, Mohamed A. Soliman. A survey of top-k queryprocessing techniques in relational database systems. ACM Computing Surveys,2008
[82]Nitin Agarwal, Huan Liu, Identifying the influential bloggers in a community,Proceedings of the international conference on Web search and web data mining,2008
[83]薛可,余阳明.人际传播学,上海同济大学出版社,2007.2
[84]王晓光.基于社会网络的知识转移研究.武汉大学博士学位论文,管理科学与工程,2007.12
[85]何明升.叩开网络化生存之门,北京:中国社会科学出版社,2005,p:120-127
[86]谢新洲,肖雯.我国网络信息传播的舆论化趋势及所带来的问题分析,情报理论与实践,2006(6)
[87]陈远.网络社区信息传播的相关理论评述.图书情报知识,2008(3)
[88]M,Cha, I tube, you tube, everybody tubes--analyzing the world's largest user generatedcontent video system, in IMC’07: Proc. Of the7thACM SIGCOMM conference onInternet measurement,2007
[89]X. Cheng,C.Dale, Statistics and social network of youtube videos, IWQoS’08:Pro. Ofthe16thInternational Workshop on Quality of Service, June2008
[90]王方芳. SNS虚拟社区交往结构与信息传播研究.大连理工大学硕士学位论文,2010.6
[91]Lailei Huang, Zhengyou Xia, Measuring User Prestige and Interaction Preference onSocial Network Site, International Conference on Computer and InformationScience,2009,p:1161-1166
[92]平亮.基于社会网络中心性分析的微博信息传播研究——以sina微博为例.信息情报与共享,2010(6):p.92~97
[93]Leskovec J, McGlohon M, Patterns of cascading behavior in large blog graphs,Proc.ofth e7th SIAM International conference on Data Mining, Minneapolis, Minnesota,USA,2007
[94]E. Adar and L.A. Adamic, Tracking information epidemics in blogspace.2005
[95]唐泳,马永开.小世界社会网络中的信息传播.系统仿真学报,2008.18(4),p.1084~1087
[96]贺悠媛,胡晓峰.基于Agent的web信息传播仿真模型.系统仿真学报,2010.22(10), p.2426~2431
[97]张嘉龄,李茂青.博客信息传播的网络模型构建.软件导刊,2008,7(5),p:67~69
[98]Cha, M., Haddadi, H., Benevenuto, Measuring user influence in twitter: The millionfollower fallacy. In Proc. of International AAAI Conference on Weblogs and SocialMedia (ICWSM),2010
[99]刘耀庭.社交网络结构研究,浙江大学硕士论文,2008.6
[100] Peng Xiaochuan,Mao Xiaodan.Social Network analysis of BBS communitycharacteristics[J],Youth Studies,2004,4,p:39-44
[101]赵战花,来向武.微博客对新闻信息传播的影响探析——基于Twitter.com.理论导刊,2010.4,p.93-95
[102] Shaozhi Ye, Felix Wu, Measuring Message Propagation and Social Influence onTwitter.com. SocInfo’10,2010,p.216-231
[103] A. Java, X.song, T. Finin, and B. Tseng.Why We Twitte: UnderstandingMicroblogging Usage and Communities, WebKDD/SNA-KDD,2007, p.201-215
[104] Louis Yu, Sitaram Asur, B. A. Huberman, What Trends in Chinese Social Media,SNA-KDD’11,2011.7:p.245-251
[105] H, Kwak, C.Lee, H. Park, and S. Moon, What is Twitter, a Social Network or aNews Media? In WWW’10,2010, p.591-600
[106] Wang, J., Lim, E.P., Jiang, J., He, Q.,TwitterRank: finding topic-sensitive influentialtwitterers, In WSDM’10,2010,p.261-270
[107] W. Chen, C. Wang, and Y. Wang. Scalable influence maximization for prevalentviral marketing in large-scale social networks. KDD’10,2010.
[108] Kimura, M., Saito, K., and Nakano, R. Extracting influential nodes for informationdiffusion on a social network. In Proceedings of the22nd AAAI Conference onArtificial Intelligence. AAAI,2007,p.1371-1376
[109]李华,赵文伟.微博客:图书馆的下一个网络新贵工具.图书与情报,2009.4,p.78-82
[110]王晓光.微博客用户行为特征与关系特征实证分析,图书情报工作.2010.14,p.66-70
[111]王晓光.微博客用户行为特征与关系特征实证分析——以“新浪微博”为例.图书情报工作,2010.7,p.66-70
[112] Zi yang,et al. Understanding Retweeting Behaviors in Social Networks,CIKM’10,2010.10,p.1633-1636
[113] Lu Liu, et al.Mining Topic-level Influence in Heterogeneous Networks, CIKM’10,2010.10, p.199-208
[114] Daniel M. Romero, Wojciech Galuba, Sitaram, Influence and Passivity in SocialMedia, WWW,2011
[115] Mark G., Stephen K.,Malik M., Finding overlapping communities in socialnetworks, IEEE International conference on social computing,2010, p.104-113
[2]唐.泰普斯科特,数字化成长：网络时代的崛起.东北财经大学出版社,1999
[3]周荣旗,方冰. Web2.0网站传播的特性比较与趋势——以Gigg与Twitter为例.网络传播,2009.11, p.60-61
[4]张瑞.“校园SNS”火爆的学理思考.传媒观察,2007.2,p.53-59
[5]能向群. SNS网络人际传播的现实化回归.新闻传播.2006.9,p.23-28
[6]张宇,在线社会网络信任计算与挖掘分析中若干模型与算法研究.博士学位论文,浙江大学,2009
[7] Leskovec J, Horvitz E. Planetary-scale views on a large instant-messaging network,Proceedings of the17thInternational Conference on World Wide Web.2008, p.915-924
[8] Xu J, Chen H, Crimenet explorer: Aframework for criminal network knowledgediscovery, ACM Transactions on Information Systems,2005,23(2), p.201-226
[9] Kempe D, Kleinberg J, Influential nodes in a diffusion model for social networks,Proceeding of the32nd International Colloquium on Automata, Languages andProgramming,2005, p.1127-1138
[10]Richardson M, Domingos P. Mining knowledge-sharing sites for viral marketing, The8thACM SIGKDD International Conference on Knowledge Discovery and DataMining,2002
[11] Java A, Kolari P, et al. Modeling th spread of influence on the blogosphere,Proceeding of the15thInternational World Wide Web Conference,2006
[12]Hill S, Provost F, Network-based marketing: Identifying likely adopters via consumernetwork, Statistical Science,2006,21(2), p.256-276
[13]段志生.图论与复杂网络.力学发展,2008,38
[14]Watts D J, Strogatz SH, Collective dynamics of small-world networks,Nature,1998,393, p.440-442
[15]Jababaie A, Lin J, Morse A S, Coordination of groups of mobile anutomomous agentsusing nearest neighbor rules, IEEE Transactions on Automatic Control,2003,48,p.988-1001
[16]薛可,余明阳.人际传播学.上海同济大学出版社,2007,2
[17]N. T. J. Bailey, The Mathematical Theory of Infectious diseases and its applications,New York, hafner Press,1975
[18]R.M. Anderson and R. M. May. Infectiious diseases of humans, Oxford, OxfordUniversity Press,1991
[19]Meade N., Islam T. Modeling and forecasting the diffusion of innovation:a25-yearreview, International Journal of Rorecasting,2006.22(3), p.519-545
[20]S. Milgram. The Small World Problem. Psychology Today,1967,60~67
[21] R. Albert, A.-L. Barabasi. Statistical Mechanics of Complex Networks. Reviews of ModernPhysics,2002,74(1):47~97
[22]Newman M. E. J. The Structure and Function of Complex Networks. SIAM Review,2003,45:167~256
[23]Malarz K, Szvetelszky Z,et al. Theory of Rumour Spreading in Complex SocialNetworks, Physica A2007.374(1),p.457-470
[24]Solmon S, Weisbuch G.,et al. Soicial percolation model, Physica A,2000,277(1),p.237-247
[25]Han J, Kamber M. Data Mining: Concepts and Techniques, Morgan Kaufmann,2001
[26]Milgram S, The small world problem, Psychology Today,1967.2
[27]Gramovetter M, The Strength of Weak Ties, American Journal of Sociology,1973.78(6)
[28]Albert R, Jeong H and Barabasi A, The Diameter of the World Wide Web, Nature,1999.401, p.130-137
[29]Newman M, The Structure of Scientific Collaboration Networks, Proceedings of theNational Academy of sciences,2001,p.409-415
[30]Amaral L, Scala A, Classes of Small-world Networks, Proceedings of the NationalAcademy of Sciences,2000, p.149-152
[31]Adamic L, Buyukkokten O, Asocial Networks Caught in the Web, First Monday,2003,8(6)
[32]Mislove A, Marcon M. Measurement and Analysis of Online SocialNetworks,Proceeding of the7th ACM SIGCOMM conference on InternetMeasurement,USA2007, p.29-42
[33]Ahn YY, Han S, Keak H, Analysis of topological characteristics of huge online socialnetworking Services, Proceedings of the16thinternatiaonal conference on World WideWeb,USA,2007, p.835-844
[34]Fu F,Liu L, Yan K, The structure of self-organized blogosphere, Physica,2006
[35]Backstrom L, Kumar R, Preferential behavior in online groups, WSDM’08,2008,.p117-128
[36]Girvab N, Newman J, Community structure in social and bilolgical networks,PNAS,2002,p7821-7826
[37]Barabasi A, Albert R, Emergence of Scaling in Ramdom Networks, Science,1999,p.9509-512
[38]Ramasco J, Dorogovtsec S, Self-organization of collaboration networks, Physica,2004.70, p.1-10
[39]Shi D H, Chen Q H, Markov Chain-based Numerical Method for Degree Distributionsfo Growing Networks, Physical,2005,71,p.36-140
[40]方锦清,毕桥,李永.复杂动态网络的一种和谐统一的混合择优模型及其普适特性.中国科学G期,2007,37, p.230-248
[41]章忠志.复杂网络的演化模型研究,博士学位论文,大连理工大学,2006
[42]Wan XJ. Yang JW. Learning information diffusion process on the web, Proceedings ofthe16thinternational conference on World Wide Web,2007,1173-1174
[43]Daniel G., R. Guha, Information diffusion throuth blogspace, Proceedings of the13thinternational World wide Web Conference, p.491-501
[44]Jure Leskovec, Mary M., Christos F., Cascading behavior in large blog graphs, SIAMInternational conference on data mining,2007
[45]Nazir A., Raza S., Unveiling facebook: a measurement study of social network basedapplications. In Proc. ACM IMC2008
[46]Nazir A., Raza S., et al, Network-level footprints of facebook applications, ACM IMC2009
[47]Fabian S., Anja F.,et al, Understanding online social network usage from a networkperspective, IMC2009, p.35-48
[48]Acquisti A., Gross R., Imagined communities: awareness, information sharing andprivacy on the Facebook. In Privacy enhancing technologies,2006
[49]Stutzman F., An evaluation of identity sharing behavior in social network communities,iDMAa Journal,2006
[50]Baker W, Faulkner R, The social organization of conspiracy, Illegal networks in theheavy electrical equipment industry, American Sociological Review,1993,58(6),p.837-860
[51]Bollen J,De Sompel, et al, Toward alternative metrics of journal impact: A comparisonof download and citation data, Information Processing&Management,2005,41(6),p.1419-1440
[52]Evertt M, Borgatti S, The centrality of groups and classes, Journal of MathematicalSociology,1999,23(3),p.181-201
[53]Newman MJ, Who is the best connected scientist? A study of scientific coauthorshipnetworks, Physical Review E,2001,64, p.337-370
[54]唐常杰,温粉莲,乔少杰.基于社会网络最短路径挖掘犯罪集团核心.计算机科学,2006,33（11）, p.23-31
[55]Page L, sergey Brin, The pagerank citation ranking: Bring order to the web, StanfordUniversity,1998
[56]Kleinberg J M, Hubs, authorities, and communities, ACM Computing surveys,1999,31
[57]Liu X, Bollen J,Nelson M,et al, Co-authorship networks in the digital library researchcommunity, Electronic commerce research and applications,2005,41, p.1462-1480
[58]Zhang J, Ackerman M S, Expertise networks in online communities: Structure andalgorithms, Proceeding of the16thInternational World Wide Web Conference,2007
[59]Peltomaki M, Alava M, Correlations in bipartite collaboration networks, Journal ofStatistical Mechanics: Theory and Experiment,2006
[60]彭小川,毛晓丹. BBS群体特征社会网络分析,青年研究.2004,4,p.39-44
[61]Peng Xiaochuan, Mao Xiaodan.Social Network analysis of BBS communitycharacteristics[J],Youth Studies,2004,4,p.39-44
[62]R.Albert, A.L.Barabasi, Statistical Mechanics of Complex Networks, Rev. Mod. Phys.2002,74, p.47-97.
[63]S.N.Dorogovtsev, J.F.F.Mendes, Evloution of networks, Adv. Phys.2002,51,p.1079-1187
[64]N.Matsumura. Y.Ohsawa. Ming and Characterizing Opinion Leaders from ThreadedOnline Discussions[J],KES2007
[65]K.-I.Goh,Y.-h.Eom, Structure and evolution of online social relationship:Heterogeneity in unrestricted discussions[J], Physical Review,2006,E73,p.066-123
[66]Zhongbao, K., Z. Changshui. Repay networks on a bulletion board system[J]. PhysicalReview E,2003,67(3),p.036-117
[67]宫辉,徐渝.高校BBS社群结构与信息传播的影响因素.西安交通大学学报,2007,27(1),p.93-96
[68]Zhang, J., M. Ackerman, and L. Adamic. Expertise networks in online communities:structure and algorithms [J]. WWW '07.2007
[69]Zhai Zhongwu, Xu Hua. Identifying opinion leaders in BBS[J], IEEE Proceedings ofWeb Intelligence and Intelligent Agent Technology,2008
[70]Barrat A,Barthelemy M, Vespingani A., Statistical Mechanics of Complex Networks,Physical Review Letters,2004,p.47-97
[71]D.J.Watts, S.H.Strogalz. Collective dynamics of small-world networks, Nature393,1998,p.440-442
[72]Hengmin zhou, Daniel Zeng, Finding leaders from opinion networks, IEEEInternational Conference on Digital Object Identifier,2009,p.266-268
[73]黄昌宁,赵海.中文分词十年回顾.中文信息学报,2007,21(3),p.8~19
[74]Newman M E, Girvan M. Finding and evaluating community structure in networks[J].Physical Review E,2004,69,p.26-39
[75]L. A. Matsunaga, N. F. F. Ebecken. Term Weighting Approaches for TextCategorization Improving[C]. in: ISDA'08, Eighth International Conference onIntelligent Systems Design and Applications,2008(1),p.409-414
[76]O. W. Kwon, J. H. Lee. Web Page Classification Based on k-Nearest NeighborApproach[C]. in: Proceedings of the5th International Workshop on InformationRetrieval with Asian Languages.2000,p.9-15
[77]A. Bergo. Text Categorization and Prototypes,the University of Amsterdam,2001
[78]苏金树,张博锋,徐昕.基于机器学习的文本分类技术研究进展.软件学报,2006,17(9), p.1848~1859
[79]T.M.Cover and PE.Hart, Rates of convergence for nearest neighbor procedure, inProc.HaWaii Int.Conf.onSystem Science.2009, p.214-223
[80]Shen yang, Shuchen li, ling zhen, Emotion mining research on micro-blog,SWS2009,p.71-75
[81]Ihab F. Ilyas, George Beskales, Mohamed A. Soliman. A survey of top-k queryprocessing techniques in relational database systems. ACM Computing Surveys,2008
[82]Nitin Agarwal, Huan Liu, Identifying the influential bloggers in a community,Proceedings of the international conference on Web search and web data mining,2008
[83]薛可,余阳明.人际传播学,上海同济大学出版社,2007.2
[84]王晓光.基于社会网络的知识转移研究.武汉大学博士学位论文,管理科学与工程,2007.12
[85]何明升.叩开网络化生存之门,北京:中国社会科学出版社,2005,p:120-127
[86]谢新洲,肖雯.我国网络信息传播的舆论化趋势及所带来的问题分析,情报理论与实践,2006(6)
[87]陈远.网络社区信息传播的相关理论评述.图书情报知识,2008(3)
[88]M,Cha, I tube, you tube, everybody tubes--analyzing the world's largest user generatedcontent video system, in IMC’07: Proc. Of the7thACM SIGCOMM conference onInternet measurement,2007
[89]X. Cheng,C.Dale, Statistics and social network of youtube videos, IWQoS’08:Pro. Ofthe16thInternational Workshop on Quality of Service, June2008
[90]王方芳. SNS虚拟社区交往结构与信息传播研究.大连理工大学硕士学位论文,2010.6
[91]Lailei Huang, Zhengyou Xia, Measuring User Prestige and Interaction Preference onSocial Network Site, International Conference on Computer and InformationScience,2009,p:1161-1166
[92]平亮.基于社会网络中心性分析的微博信息传播研究——以sina微博为例.信息情报与共享,2010(6):p.92~97
[93]Leskovec J, McGlohon M, Patterns of cascading behavior in large blog graphs,Proc.ofth e7th SIAM International conference on Data Mining, Minneapolis, Minnesota,USA,2007
[94]E. Adar and L.A. Adamic, Tracking information epidemics in blogspace.2005
[95]唐泳,马永开.小世界社会网络中的信息传播.系统仿真学报,2008.18(4),p.1084~1087
[96]贺悠媛,胡晓峰.基于Agent的web信息传播仿真模型.系统仿真学报,2010.22(10), p.2426~2431
[97]张嘉龄,李茂青.博客信息传播的网络模型构建.软件导刊,2008,7(5),p:67~69
[98]Cha, M., Haddadi, H., Benevenuto, Measuring user influence in twitter: The millionfollower fallacy. In Proc. of International AAAI Conference on Weblogs and SocialMedia (ICWSM),2010
[99]刘耀庭.社交网络结构研究,浙江大学硕士论文,2008.6
[100] Peng Xiaochuan,Mao Xiaodan.Social Network analysis of BBS communitycharacteristics[J],Youth Studies,2004,4,p:39-44
[101]赵战花,来向武.微博客对新闻信息传播的影响探析——基于Twitter.com.理论导刊,2010.4,p.93-95
[102] Shaozhi Ye, Felix Wu, Measuring Message Propagation and Social Influence onTwitter.com. SocInfo’10,2010,p.216-231
[103] A. Java, X.song, T. Finin, and B. Tseng.Why We Twitte: UnderstandingMicroblogging Usage and Communities, WebKDD/SNA-KDD,2007, p.201-215
[104] Louis Yu, Sitaram Asur, B. A. Huberman, What Trends in Chinese Social Media,SNA-KDD’11,2011.7:p.245-251
[105] H, Kwak, C.Lee, H. Park, and S. Moon, What is Twitter, a Social Network or aNews Media? In WWW’10,2010, p.591-600
[106] Wang, J., Lim, E.P., Jiang, J., He, Q.,TwitterRank: finding topic-sensitive influentialtwitterers, In WSDM’10,2010,p.261-270
[107] W. Chen, C. Wang, and Y. Wang. Scalable influence maximization for prevalentviral marketing in large-scale social networks. KDD’10,2010.
[108] Kimura, M., Saito, K., and Nakano, R. Extracting influential nodes for informationdiffusion on a social network. In Proceedings of the22nd AAAI Conference onArtificial Intelligence. AAAI,2007,p.1371-1376
[109]李华,赵文伟.微博客:图书馆的下一个网络新贵工具.图书与情报,2009.4,p.78-82
[110]王晓光.微博客用户行为特征与关系特征实证分析,图书情报工作.2010.14,p.66-70
[111]王晓光.微博客用户行为特征与关系特征实证分析——以“新浪微博”为例.图书情报工作,2010.7,p.66-70
[112] Zi yang,et al. Understanding Retweeting Behaviors in Social Networks,CIKM’10,2010.10,p.1633-1636
[113] Lu Liu, et al.Mining Topic-level Influence in Heterogeneous Networks, CIKM’10,2010.10, p.199-208
[114] Daniel M. Romero, Wojciech Galuba, Sitaram, Influence and Passivity in SocialMedia, WWW,2011
[115] Mark G., Stephen K.,Malik M., Finding overlapping communities in socialnetworks, IEEE International conference on social computing,2010, p.104-113