Purpose: This paper intends to explore a quantitative method for investigating the characteristics of information diffusion through social media like weblogs and microblogs.By using the social network analysis methods...Purpose: This paper intends to explore a quantitative method for investigating the characteristics of information diffusion through social media like weblogs and microblogs.By using the social network analysis methods,we attempt to analyze the different characteristics of information diffusion in weblogs and microblogs as well as the possible reasons of these differences.Design/methodology/approach: Using the social network analysis methods,this paper carries out an empirical study by taking the Chinese weblogs and microblogs in the field of Library and Information Science(LIS) as the research sample and employing measures such as network density,core/peripheral structure and centrality.Findings: Firstly,both bloggers and microbloggers maintain weak ties,and both of their social networks display a small-world effect. Secondly,compared with weblog users,microblog users are more interconnected,more equal and more capable of developing relationships with people outside their own social networks. Thirdly,the microblogging social network is more conducive to information diffusion than the blogging network,because of their differences in functions and the information flow mechanism. Finally,the communication mode emerged with microblogging,with the characteristics of micro-content,multi-channel information dissemination,dense and decentralized social network and content aggregation,will be one of the trends in the development of the information exchange platform in the future.Research limitations: The sample size needs to be increased so that samples are more representative. Errors may exist during the data collection. Moreover,the individual-level characteristics of the samples as well as the types of information exchanged need to be further studied.Practical implications: This preliminary study explores the characteristics of information diffusion in the network environment and verifies the feasibility of conducting a quantitative analysis of information diffusion through social media. In addition,it provides insight into the characteristics of information diffusion in weblogs and microblogs and the possible reasons of these differences.Originality/value: We have analyzed the characteristics of information diffusion in weblogs and microblogs by using the social network analysis methods. This research will be useful for a quantitative analysis of the underlying mechanisms of information flow through social media in the network environment.展开更多
面向Weblog的协同聚类算法具有同时发现用户聚类及与之对应的页面聚类的能力,已成为Weblog数据挖掘的重要研究内容。由于现有的面向Weblog的协同聚类算法大多采用硬划分方法将用户和页面分配到聚类,因此,无法很好地处理聚类边界的问题,...面向Weblog的协同聚类算法具有同时发现用户聚类及与之对应的页面聚类的能力,已成为Weblog数据挖掘的重要研究内容。由于现有的面向Weblog的协同聚类算法大多采用硬划分方法将用户和页面分配到聚类,因此,无法很好地处理聚类边界的问题,即一个用户可能属于多个聚类,从而影响了聚类质量。该文给出了一种面向Weblog的模糊协同聚类FCOW(Fuzzy CO-clustering for Weblog)算法来解决协同聚类算法的边界问题,以提高聚类结果的质量。该算法首先利用矩阵Hadamard积运算发现Weblog中隐含的独立用户模式1={,,K}PA pa pa;其次,依据pa k所对应的页面子集将剩余用户分配到该独立模式中,从而产生协同聚类结果 {k,k}CS CP,k=1,,K;最后计算每个用户和页面与协同聚类之间的模糊隶属度,并以该隶属度作为个性化推荐的依据。实验结果表明,FCOW算法具有获得高质量聚类结果的能力。展开更多
基金supported by Sun Yat-sen University Cultivation Fund for Young Teachers(Grant No.:20000-3161102)the National Social Science Fundation of China(Grant No.:08CTQ015)
文摘Purpose: This paper intends to explore a quantitative method for investigating the characteristics of information diffusion through social media like weblogs and microblogs.By using the social network analysis methods,we attempt to analyze the different characteristics of information diffusion in weblogs and microblogs as well as the possible reasons of these differences.Design/methodology/approach: Using the social network analysis methods,this paper carries out an empirical study by taking the Chinese weblogs and microblogs in the field of Library and Information Science(LIS) as the research sample and employing measures such as network density,core/peripheral structure and centrality.Findings: Firstly,both bloggers and microbloggers maintain weak ties,and both of their social networks display a small-world effect. Secondly,compared with weblog users,microblog users are more interconnected,more equal and more capable of developing relationships with people outside their own social networks. Thirdly,the microblogging social network is more conducive to information diffusion than the blogging network,because of their differences in functions and the information flow mechanism. Finally,the communication mode emerged with microblogging,with the characteristics of micro-content,multi-channel information dissemination,dense and decentralized social network and content aggregation,will be one of the trends in the development of the information exchange platform in the future.Research limitations: The sample size needs to be increased so that samples are more representative. Errors may exist during the data collection. Moreover,the individual-level characteristics of the samples as well as the types of information exchanged need to be further studied.Practical implications: This preliminary study explores the characteristics of information diffusion in the network environment and verifies the feasibility of conducting a quantitative analysis of information diffusion through social media. In addition,it provides insight into the characteristics of information diffusion in weblogs and microblogs and the possible reasons of these differences.Originality/value: We have analyzed the characteristics of information diffusion in weblogs and microblogs by using the social network analysis methods. This research will be useful for a quantitative analysis of the underlying mechanisms of information flow through social media in the network environment.
文摘面向Weblog的协同聚类算法具有同时发现用户聚类及与之对应的页面聚类的能力,已成为Weblog数据挖掘的重要研究内容。由于现有的面向Weblog的协同聚类算法大多采用硬划分方法将用户和页面分配到聚类,因此,无法很好地处理聚类边界的问题,即一个用户可能属于多个聚类,从而影响了聚类质量。该文给出了一种面向Weblog的模糊协同聚类FCOW(Fuzzy CO-clustering for Weblog)算法来解决协同聚类算法的边界问题,以提高聚类结果的质量。该算法首先利用矩阵Hadamard积运算发现Weblog中隐含的独立用户模式1={,,K}PA pa pa;其次,依据pa k所对应的页面子集将剩余用户分配到该独立模式中,从而产生协同聚类结果 {k,k}CS CP,k=1,,K;最后计算每个用户和页面与协同聚类之间的模糊隶属度,并以该隶属度作为个性化推荐的依据。实验结果表明,FCOW算法具有获得高质量聚类结果的能力。