基于复杂网络的全球新闻流动模式分析  

Analysis of Global News Flow Patterns Based on Complex Networks

作　　者：莫小梅[1] 沈浩[2] 俞定国[1] MO Xiao-mei;SHEN Hao;YU Ding-guo(College of Media Engineering,Communication University of Zhejiang,Hangzhou 310018,China;School of Journalism,Communication University of China,Beijing 100024,China)

机构地区：[1]浙江传媒学院媒体工程学院,杭州310018 [2]中国传媒大学新闻学院,北京100024

出　　处：《西南大学学报（自然科学版）》2020年第12期15-24,共10页Journal of Southwest University(Natural Science Edition)

基　　金：浙江省重点研发计划项目(2019C03138).

摘　　要：因特网的出现大大拓展了全球范围内新闻报道和传播的广度和深度,并通过在线报道的形式使世界各国前所未有地紧密联系在一起.本文根据全球整合新闻数据库(GDELT)中的GKG数据集的特点,建立国家间新闻流动网络模型;利用复杂网络理论中平均度、图密度、平均聚类系数和平均路径长度等参数对该模型拓扑特性及边权分布特点进行分析;并提出一种基于改进的互信息节点重要性评估方法.对2019年4月8日-12日期间“一带一路”国家间新闻流动为例进行实证分析的结果表明:国家间新闻流动网络具有小世界特性;其网络的权重分布具有幂律分布的特性;基于改进的互信息节点重要性评估方法可以有效挖掘出前10个重要节点国家.最后以节点重要性评估排名第一的中国为例进行了单节点分析.本文提出的分析方法为大数据时代的国家间新闻流动模式探索提供一个新的视角,同时也为我国的国际传播策略和“一带一路”建议的推动提供了一些参考.The advent of the Internet has greatly expanded the breadth and depth of news coverage and dissemination on a global scale,and online reporting has brought the world closer together than ever before.Based on the characteristics of the GKG dataset in the Global Database of Events,Language and Tone(GDELT),this paper established a news flow network model among countries.The topological characteristics and edge-weight distribution characteristics of the model are analyzed using the parameters of the complex network theory such as average degree,graph density,average clustering coefficient and average path length;and a node importance assessment method based on improved mutual information is proposed.The results of an empirical analysis of the example of news flows between the B&R countries during April 8-12,2019 show that the network of news flows between countries has small-world characteristics;and the weight distribution of its network is characterizedby a power-law distribution.Based on the improved mutual information node importance assessment method,the top 10 countries of node importance are effectively uncovered.Finally,China,which ranks the first in node importance evaluation,is taken as an example for single node analysis.The analysis method proposed in this paper provides a new perspective for the exploration of news flow pattern among countries in the era of big data,and also provides some references for China s international communication strategy and the promotion of B&R suggestions.

关 键 词：全球整合新闻数据库 复杂网络 一带一路 新闻流动模式 幂律分布 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]