文献计量学系列34: 关键词共现网络与可视化

一、加载包与导入数据

pacman::p_load(bibliometrix, rio)m1_TE <- import(file = 'E:/精鼎统计/m1_TE.xlsx')rownames(m1_TE) <- m1_TE$SRm1_TE$DE <- m1_TE$DE_TM

二、共现网络

net <- biblioNetwork(m1_TE,analysis = 'co-occurrences', network = 'author_keywords', n = 100, sep = ';', shortlabel = TRUE)#词频排名前100关键词的共词网络,返回一个稀疏矩阵str(net)# Formal class 'dgCMatrix' [package "Matrix"] with 6 slots# ..@ i : int [1:6956] 0 1 2 3 4 5 6 7 8 9 ...# ..@ p : int [1:101] 0 100 200 300 399 497 595 692 790 886 ...# ..@ Dim : int [1:2] 100 100# ..@ Dimnames:List of 2# .. ..$ : chr [1:100] "CATCHMENT" "STABLE-ISOTOPE" "RUNOFF" "GROUNDWATER" ...# .. ..$ : chr [1:100] "CATCHMENT" "STABLE-ISOTOPE" "RUNOFF" "GROUNDWATER" ...# ..@ x : num [1:6956] 205 74 82 64 54 75 54 61 38 35 ...# ..@ factors : list()netstat <- networkStat(net, stat = 'all', type = 'degree')#网络特征统计,返回1个列表,更改type参数可以获得不同的相似度指数。summary(netstat, k = 10)#总结网络特征统计# Main statistics about the network# Size 100 # Density 0.693 # Transitivity 0.758 # Diameter 2 # Degree Centralization 0.307 # Average path length 1.307 # # # Main measures of centrality and prestige of vertices# Degree Centrality: Top vertices# Vertex ID Degree Centrality# 1 CATCHMENT 1.00# 2 STABLE-ISOTOPE 1.00# 3 RUNOFF 1.00# 4 GROUNDWATER 0.99# 5 PRECIPITATION 0.98# 6 RUNOFF-GENERATION 0.98# 7 TRACER 0.98# 8 DEUTERIUM 0.98# 9 MODEL 0.97# 10 FLOW 0.97

三、共词网络可视化

netgraph <- networkPlot(net, degree = 1, Title = 'Keywords co-occurrences', type = 'auto',#更改图形形状 size = 0.5, label.color = T, labelsize = 3, label.cex = TRUE, label.n = NULL, curved = 0.4, remove.isolates = FALSE, edges.min = 5, edgesize = 1)

图1 type = "auto",关键词共现网络

Type参数值可为"auto","circle","sphere","mds", "fruchterman", "kamada"。参数不一样,图形形状有差异。更改type参数值type = "circle",其他参数不变,如图2。
图2 type = "circle",关键词共现网络
大家可以多试试,看看图形效果,然后选择合适的图形。
net2VOSviewer(netgraph, vos.path = "E:/Software/VOSviewer_1.6.15_jar")#在VOSviewer中视图
图3 VOSviewer关键词共词网络
从图1-3,我们可以清晰地看到关键词被分为2类主题。第一类主题以流域、径流形成等为代表,第二类主题以稳定同位素、地下水和降雨为代表。

四、小结

biblioNetwork函数,除了之前我们介绍的作者、机构和国家合作网络和本期的共词网络外,还可以做引文和共被引网络分析,有兴趣的同学可以看官方帮助文档。


(0)

相关推荐