机构合作网络的特征挖掘及演化分析

The Feature Mining and Evolution Analysis of the Institutional Collaboration Network

文章应用复杂网络的相关知识,对国内的医药学文献数据进行数据挖掘.以机构为研究对象,通过构建机构科研合作网络,对网络的静态参数、拓扑结构、动态演化进行挖掘分析,找出机构间科研合作网的静态特征,并以年为单位切分时间片,分析网络的动态演化特征.通过研究得出机构合作网络的静态参数,同时发现,机构科研合作网络有明显的局部化特征,它的主网络是一个小世界网络,具有无标度特性.机构的影响力和活跃度不仅体现在发文量上,同时也体现在与其他机构的合作程度上.

This paper has not only constructed the networks of institutional collaborations by using data of Chinese biomedical literatures, but also studied many statistical properties of the networks through the segment of network in years, such as static parameters, dynamic evolution topology. We found out the static features of the institutional collaboration network. The institutional collaboration network, which shows significant local features, is a ＂small world＂ network with the properties of scale free. Moreover, the influence and active state of an institution is reflected not only in the quantity of literatures of a institution, but also in the level of the collaboration with others.