特殊事件中国际关系网络时序演化分析

Sequential Evolution Analysis of International Relations Network in Special Events

21世纪以来的国际关系错综复杂、瞬息万变,给世界的经济、政治、安全、外交等带来了深刻影响。及时掌握国际关系的变化对中国外交政策制定、整体发展规划有着极为重要的意义。随着大数据时代的来临,应用大数据方法结合国际关系定量分析的工具对国际关系变化模式进行及时、有效地挖掘成为了一个重要的议题。强时效性、高信息量的新闻事件大数据蕴含能及时地反映出国际事件影响全球国际关系的信息。网络化挖掘作为一种面向大数据的信息挖掘方法,因其具象化的关系表达方式和丰富的结构分析方法组成为数据驱动的国际关系研究的重要方法。以短期国际事件为背景,对新闻事件大数据进行网络化挖掘,进行国际关系网络的时序演化分析,能够在短期国际事件造成国际关系变化的场景下,提供应对国际关系变化的解决方案参考。本文以中美贸易战为例研究特殊事件中国际关系网络的时序演化模式:基于GDELT新闻事件数据进行国际关系网络的构建,利用复杂网络方法进行信息挖掘并进行国际关系分析。首先利用该数据构建国际关系网络,然后用动态社区划分方法对其进行时序演化模式探测,最后结合点分布模式、核密度分析、空间自相关等空间分析方法对其进行空间特性分析。研究发现:①在特殊事件发生过程中,网络社区的演化方式与发生的子事件类型具有很强的相关性;②同一社区的节点在空间分布上一般呈现明显的聚集特征,特定区域节点加入不同社区频率高,节点网络属性值的空间高值分布随事件发生而改变;③网络局部特征值随子事件发生往往会发生较大变化。本文的研究为短期国际事件中的国际关系动态变化实证分析提供了一个新的视角,为国际关系研究的空间转向提供了一个新的思路,在方法层面对数据驱动的国际关系研究进行了补充,同时也为大数据的网络化挖掘提供了参考。

Since the beginning of the 21 stcentury, the complex and fast-changing international relations have brought profound effects to the world economy, politics, security, and diplomacy. Keeping abreast of the changes in international relations is of great significance to China’s foreign policy making and overall development planning. With the advent of the era of big data, the application of big data combined with quantitative analysis tools of international relations to timely and effectively mine the change patterns of international relations has become an important issue. Big data of news events with strong timeliness and high information content can timely reflect the information that international events affect global international relations. As an information mining method oriented to big data, network mining is a good choice for data-driven international relations research because of its figurative relational expression and rich structural analysis methods. Taking short-term international events as the background, the network mining of big data of news events and the sequential evolution analysis of international relations network can provide solutions to the changes of international relations in the context of changes of international relations caused by short-term international events. This paper takes the Trade War between China and the United States as an example to study the temporal evolution pattern of the international relations network in special events. Based on the GDELT news event data, the international relations network is constructed, and methods based on complex network theory are used for information mining and analysis of international relations. Firstly, the data are used to construct the international relationship network, then the temporal evolution patterns are detected by dynamic community partition method, and finally the spatial characteristics are analyzed by combining the spatial analysis methods such as analysis of point distribution patterns, nuclear density analysis, and spatial autocorrelation analysis. The results show that:(1) In the process of the occurrence of special events, there is a strong correlation between the evolution of the network community and the type of sub-events;and(2) Nodes in the same community generally show obvious clustering characteristics in spatial distribution. Nodes in a specific region join different communities with high frequency.The spatial distribution of the high values of node network attribute changes with the occurrence of events. The local eigenvalues of the network change dramatically with the occurrence of sub-events. The research in this paper provides a new perspective for the empirical analysis of the dynamic changes of international relations in short-term international events, provides a new idea for the spatial shift of international relations research,complements the data-driven international relations research at the methodological level, and also provides a reference for the network mining of big data.