基于学科布局的科研机构层次聚类模型构建与实证分析

Model Construction and Empirical Analysis of Institute Hierarchical Clustering Based on Discipline Layout

研究不同机构学科布局或主题领域分布的差异,并基于学科布局对科研机构进行聚类分析,有助于掌握科研机构的发展规律,对提高机构管理的效率和效益方面有着重要意义.文章采用科学基金项目数据来衡量科研机构学科布局情况,并针对基于项目数据学科布局聚类过程中数据存在的高维、稀疏特征,传统的聚类方法难以直接处理的问题,构建了“t-SNE+层次聚类”集成聚类方法.通过对中国科学院的国家自然科学基金项目数据进行研究,得到了中国科学院下属的117个研究机构的基于学科布局的聚类结果,并以10类为例,阐述了不同类别的机构学科布局特征.实证结果表明,文章使用的“t-SNE+层次聚类”方法得到的聚类结果,相比于传统方法得到的结果具有更好的效果,可以为学科布局调整提供支撑.

Studying the differences in the distribution of subject areas or subject areas in different institutions, and clustering analysis of scientific research institutions based on the subject layout, it is helpful to grasp the development law of scientific research institutions, and it is of great significance to improve the efficiency and efficiency of institutional management. It has always been an important issue. In this paper, the science fund project data is used to measure the academic layout of scientific research institutions, and the high-dimensional and sparse features of the data in the clustering process based on the project data discipline layout are difficult to deal with directly by the traditional clustering method. SNE+ hierarchical clustering integration method. Through the research on the application data of the Natural Science Foundation of the Chinese Academy of Sciences, the clustering results based on the disciplinary layout of 117 research institutions affiliated to the Chinese Academy of Sciences were obtained, and 10 categories were used as examples to illustrate the characteristics of different categories of institutional disciplines. The empirical results show that the clustering results obtained by the "t-SNE+ hierarchical clustering" method in this paper are better than the results obtained by the traditional methods.