图书情报工作

图书情报工作 >

2022 , Vol. 66 >Issue 21: 107 - 119

DOI: https://doi.org/10.13266/j.issn.0252-3116.2022.21.012

知识组织

优化科学知识图谱方法绘制全领域科学结构图谱

  • 陈挺 ,
  • 李国鹏 ,
  • 王小梅
展开
  • 1 中国科学院科技战略咨询研究院 北京 100190;
    2 中国科学院大学经济与管理学院图书情报与档案管理系 北京 100190;
    3 中国科学院文献情报中心 北京 100190
陈挺,副研究员,博士研究生;李国鹏,助理研究员,硕士;王小梅,研究馆员,硕士,E-mail:wangxm@casisd.cn。

收稿日期: 2021-10-11

  修回日期: 2022-07-17

  网络出版日期: 2022-11-25

基金资助

本文系中国科学院文献情报能力建设专项"重要领域战略情报研究与重点成果"（项目编号：GHJ-QBZX-2021-04）研究成果之一。

收起

Optimizing Science Knowledge Mapping Methods to Map the Global Science Structure Graph

  • Chen Ting ,
  • Li Guopeng ,
  • Wang Xiaomei
Expand
  • 1 Institutes of Science and Development, Chinese Academy of Sciences, Beijing 100190;
    2 Department of Library, Information and Archives Management, School of Economics and Management, University of Chinese Academy of Sciences, Beijing 100190;
    3 National Science Library, Chinese Academy of Sciences, Beijing 100190

Received date: 2021-10-11

  Revised date: 2022-07-17

  Online published: 2022-11-25

Fold

摘要

[目的/意义] 针对目前全领域科学知识图谱构建方法中存在的技术难点，结合网络嵌入模型、机器学习聚类、流形学习可视化算法等人工智能领域的方法与模型，提出一套全新发现科学结构的知识图谱构建方案，以完善科学结构发现与可视化布局，并拓展科学知识图谱的分析应用场景。[方法/过程] 引入基于深度学习的网络嵌入模型和聚类方法改进原有的网络社团划分聚类方法，利用流形学习降维可视化算法扩大数据处理能力，并设计由下至上分层可视化布局方法，提升可视化图谱的稳定性与细节揭示能力。[结果/结论] 以科睿唯安公司的基本科学指标数据库（ESI）研究前沿中高被引论文作为分析数据集，使用新聚类算法得到1 169个研究领域，通过改进的可视化布局算法形成全领域科学结构图谱。与前几期科学结构图谱相比，本文提出的方法支持更大规模的数据分析，对可视化细节揭示与稳定性也有大幅优化，可以更好地展示全领域科学研究宏观结构及内在关系，为全领域科学知识图谱的绘制与构建提供更可靠的方法和技术支持。

关键词： 科学图谱; 科学结构; 引文网络; 网络嵌入; 聚类; 可视化

本文引用格式

陈挺 , 李国鹏 , 王小梅 . 优化科学知识图谱方法绘制全领域科学结构图谱[J]. 图书情报工作, 2022 , 66(21) : 107 -119 . DOI: 10.13266/j.issn.0252-3116.2022.21.012

Abstract

[Purpose/Significance] To address the technical difficulties in the construction of the current domain-wide science knowledge graph, this study proposes a new knowledge graph construction scheme for discovering scientific structures by combining methods and models in the field of machine learning such as network embedding models, machine learning clustering and manifold learning visualization algorithms, and to improve scientific structure discovery and visualization methods and further expand the analysis application scenarios of science knowledge graph.[Method/Process] A deep learning-based network embedding model and clustering method were introduced to improve the original network association partitioning clustering method, a stream learning dimensionality reduction visualization algorithm was used to expand the data processing capability, and a bottom-up hierarchical visualization method was designed to improve the stability and detail revealing capability of the map.[Result/Conclusion] Using the Clarivate's Essential Science Indicators (ESI) highly cited papers as the test analysis dataset, 1,169 research areas are obtained by new clustering method, and a global scientific structure map is formed through an improved visual layout algorithm. Compared with the previous science maps, the method proposed in this paper supports larger scale data analysis, and the visualization details reveal and stability are greatly optimized, which can better demonstrate the macro structure and inner relationship of scientific research in the whole domain within a time period, and provide more reliable methods and technical support for the mapping and construction of global science map.

Key words： science mapping; science structure; citation network; network embedding; clustering; visualization

参考文献

[1] 邱均平, 王曰芬. 文献计量内容分析法[M]. 北京:国家图书馆出版社, 2008.
[2] RASMUSSEN E, ATKINS H B, BORNER K, et al.Visualizing knowledge domains[C]//Proceedings of the American Society for Information Science and Technology. Aachen:Wiley, 2002, 39(1):476-477.
[3] ECK N, WALTMAN L. Software survey:VOSviewer, a computer program for bibliometric mapping[J].Scientometrics, 2010, 84(2):523-538.
[4] Indiana university and scitech strategies, Sci2 Team. Science of science (Sci2) tool[EB/OL].[2022-07-11].https://sci2.cns.iu.edu.
[5] CHEN C.CiteSpace II:detecting and visualizing emerging trends and transient patterns in scientific literature[J]. Journal of the American Society for Information Science and Technology, 2006, 57(3):359-377.
[6] COBO M J,CHICLANA, COLLOP A, et al. A bibliometric analysis of the intelligent transportation systems research based on science mapping[J]. Intelligent transportation systems, 2014,15(2):901-908.
[7] MURGADO-ARMENTEROS E M,GUTIÉRREZ-SALCEDO M, TORRES-RUIZ F J, et al. Analysing the conceptual evolution of qualitative marketing research through science mapping analysis[J]. Scientometrics, 2015,102(1):519-557.
[8] RUOYU J, YUAN H, QIAN C. Science mapping approach to assisting the review of construction and demolition waste management research published between 2009 and 2018[J]. Resources, conservation and recycling, 2019, 140:175-188.
[9] 侯海燕, 刘则渊, 栾春娟. 基于知识图谱的国际科学计量学研究前沿计量分析[J]. 科研管理, 2009(1):164-170.
[10] 范天田, 宋胜文, 李会,等. 脓毒症科学计量学图谱特征[J]. 中华危重病急救医学, 2021, 33(4):433-437.
[11] 中国科学院战略咨询研究院. 科学结构图谱2021[R].[2022-04-17]. http://sciencemap.casaid.cn/.
[12] 王小梅, 邓启平, 李国鹏,等. ESI研究前沿的科学图谱及在纳米领域的应用[J]. 图书情报工作, 2017, 61(12):106-112.
[13] 王小梅, 韩涛, 王俊,等. 基于同被引分析的科学结构图[J]. 科学观察, 2009, 4(4):1-15.
[14] 王小梅, 韩涛, 王俊. 把握复杂科学结构揭示创新动态趋势——《科学结构地图》系列专著介绍[J]. 中国科学院院刊, 2012, 27(6):759-763.
[15] 王小梅, 李国鹏, 陈挺. 科学结构地图2017[M]. 北京:科学出版社, 2015.
[16] 潘教峰, 张晓林, 王小梅,等. 科学结构地图2012[M]. 北京:科学出版社, 2012.
[17] 王小梅, 邓启平. 科学结构地图的领域群自动识别研究[J]. 现代图书情报技术, 2016, 32(4):48-55.
[18] 王小梅, 李国鹏, 陈挺. 中国与世界主要科技强国的科学资助分析:基于科学结构图谱2010-2015[J]. 中国科学基金, 2018, 32(4):424-433.
[19] CHEN T, LI G, DENG Q, et al. Using network embedding to obtain a richer and more stable network layout for a large scale bibliometric network[J]. Journal of data and information science, 2020,6(1):154-177.
[20] PRICE D J. Networks of scientific papers[J]. Science,1965,149(3683):510-515.
[21] SMALL H. Visualizing science by citation mapping[J]. Journal of the American Society for Information Science, 1999, 50(9):799-813.
[22] 文部科学省科学技术政策研究所. 科学技术指标2017[EB/OL].[2022-07-11]. http://data.nistep.go.jp/dspace/bitstream/11035/3178/3/NISTEP-RM261-Full_J.pdf.
[23] Institute for scientific information. Global research report identifying research fronts in the Web of science:from metrics to meaning[R].[2022-04-17].https://clarivate.com/blog/identifying-research-fronts-in-the-web-of-science-from-metrics-to-meaning/ni.
[24] HAREL D, KOREN Y. On clustering using random walks[C]//Proceedings of the conference on foundations of software technology & theoretical computer science. Berlin:Springer, 2001:18-41.
[25] TRAAG V A, WALTMAN L, VAN ECK N J. From louvain to leiden:guaranteeing well-connected communities[J]. Scientific reports, 2019, 9(1):5233.
[26] GIBSON H, FAITH J, VICKERS P. A survey of two-dimensional graph layout techniques for information visualisation[J].Information visualization,2013, 12(3/4):324-357.
[27] BATTISTA G D, EADES P, TAMASSIA R, et al. Graph drawing:algorithms for the visualization of graphs[M]. Upper Saddle River:Prentice Hall,1999.
[28] MARTIN S, BROWN W M, KLAVANS R, et al. OpenOrd:an open-source toolbox for large graph layout[C]//International Society for Optics and Photonics Visualization and Data Analysis 2011. Ontario:2011,786806.
[29] WALTMAN E L. Software survey:VOSviewer, a computer program for bibliometric mapping[J]. Scientometrics, 2010, 84(2):523-538.
[30] MCINNES L, HEALY J, ASTELS S. Hdbscan:hierarchical density based clustering[J]. The journal of open source software, 2017, 2(11):205.
[31] SZÉKELY G J,RIZZO M L. Hierarchical clustering via joint between-within distances:extending ward's minimum variance method[J]. Journal of classification,2005,22(2):151-183.
[32] PEROZZI B, AL-RFOU R, SKIENA S. DeepWalk:online learning of social representations[C]//Proceedings of the 20th ACM SIGKDD international conference on knowledge discovery and data mining. New York:ACM, 2014:701710.
[33] GROVER A, LESKOVEC J. Node2Vec:scalable feature learning for networks[C]//Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining. San Francisco:ACM, 2016:855-864.
[34] JIAN T, MENG Q, WANG M, et al. LINE:large-scale information network embedding[C]//Proceedings of the 24th international conference on World Wide Web. Florence:Association for Computing Machinery, 2015:1067-1077.
[35] SHEN Z, CHEN F, YANG L, et al. Node2vec representation for clustering journals and as a possible measure of diversity[J]. Journal of data and information science, 2019, 4(2):79-92.
[36] XIAO C, SUN L, HAN J, et al. Heterogeneous academic network embedding based multivariate random-walk model for predicting scientific impact[J]. Applied intelligence, 52(2):2171-2188.
[37] VAN DER MAATEN L, HINTON G. Visualizing data using t-SNE[J]. Journal of machine learning research, 2008, 9(11):2579-2605.
[38] LI W, CERISE J E, YANG Y, et al. Application of t-SNE to human genetic data[J]. Journal of bioinformatics & computational biology, 2017, 15(4):1750017.
[39] LIU S S, BREMER P T, THIAGARAJAN J J, et al. Visual exploration of semantic relationships in neural word embeddings[J]. IEEE transactions on visualization and computer graphics, 2018, 24(1):553-562.
[40] 李阳, 张亚非, 苗壮,等. 基于t-SNE卷积编码的图像检索方法[J]. 计算机应用研究, 2017, 34(4):1244-1248.
[41] 陈挺, 李国鹏, 王小梅. 基于t-SNE降维的科学基金资助项目可视化方法研究[J]. 现代图书情报技术, 2018, 2(8):1-9.
Options
文章导航

/

〈 〉