朱炤瑗;秦昆;关庆锋;罗萍;姚博睿;漆林;周扬;
ZHU Zhao-yuan;QIN Kun;GUAN Qing-feng;LUO Ping;YAO Bo-rui;QI Lin;ZHOU Yang;School of Remote Sensing and Information Engineering,Wuhan University;School of Geography and Information Engineering,China University of Geosciences,Wuhan;

• 1:武汉大学遥感信息工程学院
• 2:中国地质大学(武汉)地理与信息工程学院

摘要(Abstract)：

COVID-19疫情不断蔓延为国际政治、外交关系等带来深刻影响。目前基于复杂网络方法的国际关系研究较少考虑节点的空间属性,难以探索国际关系的动态演化模式及其空间分布特征。该文提出一种结合时间序列聚类与空间统计的国家关系交互网络演化模式探测方法。基于2020年1月-2021年3月的GDELT数据构建国家关系交互网络,基于节点的演化特征,应用K-means聚类算法将节点划分为6种类型,结合局部连接统计方法分析节点演化模式的空间分布特征。研究表明:面对疫情冲击,各国为控制疫情蔓延倾向于参与合作交互事件;国家关系交互网络中的不同时序演化模式总体按照节点的点度中心性强度由高到低分布;疫情防控期间网络中始终处于边缘地位的节点在空间分布上呈现聚集特征,而核心节点空间分布较分散。通过研究网络节点的时序演化模式及空间分布特征可为公共卫生危机事件期间国际关系与地缘政治研究提供新思路,对于危机事件期间制定外交政策与应对策略具有一定参考价值。
The spreading of COVID-19 across the world has a profound impact on international politics and diplomatic relations.The international relations have become intricate and unpredictable during the COVID-19 pandemic.Therefore, spatiotemporal analysis of international relations has important reference value for China′s diplomatic development.In this paper, we propose an evolution pattern detection method for international relations network to study the spatiotemporal evolution pattern of international relations during the COVID-19 pandemic based on time series clustering algorithm and spatial statistics method.Based on the GDELT data from January 2020 to March 2021,the international relations network is constructed.According to the temporal evolution characteristics of nodes in the network, the nodes are divided into six types by using K-means clustering algorithm with dynamic time warping(DTW) distance, and the spatial distribution characteristics of node evolution patterns are analyzed by combining join-counts method.The results show that: 1) During the COVID-19 pandemic, most countries prefer cooperating with other countries to curb the spread of the disease. 2) The temporal evolution patterns in international relations network during the COVID-19 pandemic are arranged from high to low according to the degree centrality of nodes. 3) The peripheral nodes in international relations network are spatially clustered, while the core nodes are dispersed in spatial distribution. The research in this paper provides a new perspective for the international relations and geo-politics research in public health crisis events, and provides a reference for China′s diplomatic development.

关键词(KeyWords)： COVID-19;GDELT数据;时间序列聚类;国际关系;复杂网络;时空分析
COVID-19;GDELT data;time series clustering;international relations;complex network;spatial-temporal analysis

Abstract:

Keywords:

基金项目(Foundation): 国家重点研发计划项目“地理大数据挖掘与时空模式发现”(2017YFB0503600);; 国家自然科学基金项目“全球尺度地理多元流的网络化挖掘及关联分析”(42171448)

作者(Authors): 朱炤瑗;秦昆;关庆锋;罗萍;姚博睿;漆林;周扬;
ZHU Zhao-yuan;QIN Kun;GUAN Qing-feng;LUO Ping;YAO Bo-rui;QI Lin;ZHOU Yang;School of Remote Sensing and Information Engineering,Wuhan University;School of Geography and Information Engineering,China University of Geosciences,Wuhan;

参考文献(References)：

• [1] 龚向前.传染病控制之国际法问题研究[D].武汉：武汉大学，2005.
• [2] 张宇燕，倪峰，杨伯江，等.新冠疫情与国际关系[J].世界经济与政治，2020(4):4-26.
• [3] 薛浩男，张雪英，吴明光，等.基于新闻数据的新冠疫情事件下“全球—中国”国际关系变化分析方法[J].地球信息科学学报，2021,23(2):351-363.
• [4] 李义虎.无政府、自助，还是人类命运共同体?——全球疫情下的国际关系检视[J].国际政治研究，2020,41(3):20-25.
• [5] 李海东.疫情深刻改变国际关系格局[N].环球时报，2020-03-31(14).
• [6] BRAMS S J.Transaction flows in the international system[J].The American Political Science Review,1966,60(4):880-898.
• [7] SKJELSBAEK K.Peace and the structure of the international organization network[J].Journal of Peace Research,1972,9(4):315-330.
• [8] BRAMS S.The structure of influence relationships in the international system[A].International Politics and Foreign Policy:A Reader in Research and Theory[M].Free Press,1969.583-599.
• [9] 陈小强，袁丽华，沈石，等.中国及其周边国家间地缘关系解析[J].地理学报，2019,74(8):1534-1547.
• [10] WANG Q Y,CAO S Y,XIAO Y Y.Statistical characteristics of international conflict and cooperation network[J].Physica A:Statistical Mechanics and Its Applications,2019,535:1-10.
• [11] 秦昆，罗萍，姚博睿.GDELT数据网络化挖掘与国际关系分析[J].地球信息科学学报，2019,21(1):14-24.
• [12] DU R J,WANG Y,DONG G G,et al.A complex network perspective on interrelations and evolution features of international oil trade,2002-2013[J].Applied Energy,2017,196:142-151.
• [13] WANG M G,TIAN L X,DU R J.Research on the interaction patterns among the global crude oil import dependency countries:A complex network approach[J].Applied Energy,2016,180:779-791.
• [14] 熊文，罗熙，孙婷，等.基于北极航道开通情景的世界贸易网络演进分析[J].地理与地理信息科学，2021,37(3):109-119.
• [15] LEETARU K,SCHRODT P A.GDELT:Global Data on Events,Location,and Tone,1979-2012[C].ISA Annual Convention,2013,2(4):1-49.
• [16] 汪小帆，李翔，陈关荣.复杂网络理论及其应用[M].北京：清华大学出版社有限公司，2006.
• [17] 原继东，王志海.时间序列的表示与分类算法综述[J].计算机科学，2015,42(3):1-7.
• [18] RAKTHANMANON T,CAMPANA B,MUEEN A,et al.Searching and mining trillions of time series subsequences under dynamic time warping[A].Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining[C].2012.262-270.
• [19] MCGOVERN A,ROSENDAHL D H,BROWN R A,et al.Identifying predictive multi-dimensional time series motifs:An application to severe weather prediction[J].Data Mining and Knowledge Discovery,2011,22(1):232-258.
• [20] 邸少宁，朱杰，郑加柱，等.出租车轨迹数据的南京人群出行模式挖掘[J].测绘科学，2021,46(1):203-212.
• [21] YANG J,SUN Y,SHANG B,et al.Understanding collective human mobility spatiotemporal patterns on weekdays from taxi origin-destination point data[J].Sensors,2019,19(12):2812.
• [22] HUI D,TRAJCEVSKI G,SCHEUERMANN P I,et al.Querying and mining of time series data[J].Proceedings of the VLDB Endowment,2008,1(2):1542-1552.
• [23] YUAN Y H,RAUBAL M.Extracting dynamic urban mobility patterns from mobile phone data[A].International Conference on Geographic Information Science[C].2012.354-367.
• [24] 冀敏杰，肖利雪.一种时间序列数据的动态K-means聚类算法[J].计算机与数字工程，2020,48(8):1852-1857.
• [25] 吴广建，章剑林，袁丁.基于K-means的手肘法自动获取K值方法研究[J].软件，2019,40(5):167-170.
• [26] 冯长强，刘宗毅，曹一冰，等.地理信息系统在地缘领域中的应用与展望[J].地理与地理信息科学，2020,36(3):76-82.
• [27] ANSELIN L,LI X.Operational local join count statistics for cluster detection[J].Journal of Geographical Systems,2019,21(2):189-210.