-
Notifications
You must be signed in to change notification settings - Fork 1
/
1_thematic_maps.R
278 lines (221 loc) · 10.1 KB
/
1_thematic_maps.R
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
#Thematic mapping
# library
library(bibliometrix)
# readRDS (optional)
MCE <- readRDS("data/MCE.RDS")
# Timeslices -----------------------------------------------------------------
# timeslices 2000-2018
MCE1 <- subset(MCE, PY < 2019)
years <- c(2012, 2015)
TMslice <- timeslice(MCE1, breaks = years)
names(TMslice)
NROW(TMslice$`(2000,2012]`) # 224 papers
NROW(TMslice$`(2012,2015]`) # 227 papers
NROW(TMslice$`(2015,2018]`) # 1723 papers
# timeslice 2019
i <- MCE$PY < 2019
subdf <- subset.data.frame(MCE, subset = i)
restdf <- subset.data.frame(MCE, subset = !i)
early <- subset.data.frame(MCE, subset = is.na(i)) #add early access papers in the 2019 dataset as they did not have 2019 in PY column yet
MCE2 <- rbind(restdf,early)
# Analysis -----------------------------------------------------------------
library(igraph) # required for exporting the network files
# variables
mF <- 5 # minimum Frequency
n <- 1000 # number of terms to be included in the analysis
# timeslice 2000-2012
tmce1 <- thematicMap(TMslice$`(2000,2012]`, field ="DE", n = n, minfreq = mF, stemming = FALSE, repel = TRUE)
words0012 <- as.data.frame(tmce1$words) # to check which words are in a cluster (OPTIONAL)
write_graph(tmce1$net$graph_pajek, file = "thematic_network_2000-2012.net", format = "pajek")
#timeslice 2013-2015
tmce2 <- thematicMap(TMslice$`(2012,2015]`, field ="DE", n = n, minfreq = mF, stemming = FALSE, repel = TRUE)
words1315 <- as.data.frame(tmce2$words)
write_graph(tmce2$net$graph_pajek, file = "thematic_network_2013-2015.net", format = "pajek")
# timeslice 2016-2018
tmce3 <- thematicMap(TMslice$`(2015,2018]`, field ="DE", n = n, minfreq = mF, stemming = FALSE, repel = TRUE)
words1618 <- as.data.frame(tmce3$words)
write_graph(tmce3$net$graph_pajek, file = "thematic_network_2016-2018.net", format = "pajek")
# timeslice 2019
tmce4 <- thematicMap(MCE2, field ="DE", n = n, minfreq = mF, stemming = FALSE, repel = TRUE)
words19 <- as.data.frame(tmce4$words)
write_graph(tmce4$net$graph_pajek, file = "thematic_network_2019.net", format = "pajek")
# Plots -----------------------------------------------------------------
# standard plots
# plot(tmce1$map)
# plot(tmce2$map)
# plot(tmce3$map)
# plot(tmce4$map)
# ggplot
library("ggplot2")
library("ggrepel")
# change labels if necessary by modifying tm$clusters
# tm1
tmce1$clusters[1,7] <- "Circular Economy (CE)"
tmce1$clusters[3,7] <- "China and Industrial Ecology"
# tm2
tmce2$clusters[3,7] <- "CE and sustainab*"
tmce2$clusters[1,7] <- "china and industrial symbiosis"
tmce2$clusters[2,7] <- "Life Cycle Assessment (LCA)"
# tm3
tmce3$clusters[6,7] <- "CE, sustainab*, LCA, waste mgmt."
tmce3$clusters[7,7] <- "cleaner production and CSR"
tmce3$clusters[15,7] <- "zero waste and SDGs"
# tm4
tmce4$clusters[1,7] <- "CE, sustainab*, recycling, LCA"
tmce4$clusters[14,7] <- "design"
#2000-2012 ----
# prepare values for plot
tm <- tmce1
size <- 0.8
meandens = mean(tm$clusters$rdensity)
meancentr = mean(tm$clusters$rcentrality)
rangex = max(c(meancentr - min(tm$clusters$rcentrality), max(tm$clusters$rcentrality) -
meancentr))
rangey = max(c(meandens - min(tm$clusters$rdensity), max(tm$clusters$rdensity) -
meandens))
xlimits = c(meancentr - rangex, meancentr + rangex)
ylimits = c(meandens - rangey, meandens + rangey)
# plot tmce1
library(ggplot2)
library(ggrepel)
#export pdf
pdf(file = "tmce1.pdf", width = 3.54331, height = 3.54331)
#ggplot
g = ggplot(tm$clusters, aes(x = tm$clusters$rcentrality, y = tm$clusters$rdensity, text = (tm$clusters$words))) +
geom_point(group = "NA", aes(size = log(as.numeric(tm$clusters$freq))),
shape = 20, col = adjustcolor(tm$clusters$color, alpha.f = 0.5))
g = g + geom_hline(yintercept = meandens, linetype = 2, size = 0.3, color = adjustcolor("black",alpha.f = 0.7)) +
geom_vline(xintercept = meancentr, linetype = 2, size = 0.3, color = adjustcolor("black", alpha.f = 0.7))
g = g + geom_label_repel(aes(group = "NA", label = ifelse(tm$clusters$freq > 1, unlist(tolower(tm$clusters$name)), "")),
size = 1.2 * (1 + size), angle = 0,
label.size = 0.1) #changed
g = g + theme_bw() + #new
theme(legend.position = "none") +
scale_radius(range = c(5 * size, 60 * size)) +
labs(x = "Centrality", y = "Density") +
xlim(xlimits) +
ylim(ylimits) +
theme(axis.text.x = element_blank(),
axis.ticks.x = element_blank(),
axis.text.y = element_blank(),
axis.ticks.y = element_blank(),
plot.background = element_blank(), #new
panel.grid = element_blank()) #new
g
dev.off() #stop pdf export
# 2013-2015 -----------------------------------------------------------------
#prepare values for plot
tm <- tmce2
size <- 0.8
meandens = mean(tm$clusters$rdensity)
meancentr = mean(tm$clusters$rcentrality)
rangex = max(c(meancentr - min(tm$clusters$rcentrality), max(tm$clusters$rcentrality) -
meancentr))
rangey = max(c(meandens - min(tm$clusters$rdensity), max(tm$clusters$rdensity) -
meandens))
xlimits = c(meancentr - rangex, meancentr + rangex)
ylimits = c(meandens - rangey, meandens + rangey)
# plot tmce1
#export pdf
pdf(file = "tmce2.pdf", width = 3.54331, height = 3.54331)
#ggplot
g = ggplot(tm$clusters, aes(x = tm$clusters$rcentrality, y = tm$clusters$rdensity, text = (tm$clusters$words))) +
geom_point(group = "NA", aes(size = log(as.numeric(tm$clusters$freq))),
shape = 20, col = adjustcolor(tm$clusters$color, alpha.f = 0.5))
g = g + geom_hline(yintercept = meandens, linetype = 2, size = 0.3, color = adjustcolor("black",alpha.f = 0.7)) +
geom_vline(xintercept = meancentr, linetype = 2, size = 0.3, color = adjustcolor("black", alpha.f = 0.7))
g = g + geom_label_repel(aes(group = "NA", label = ifelse(tm$clusters$freq > 1, unlist(tolower(tm$clusters$name)), "")),
size = 1.2 * (1 + size), angle = 0,
label.size = 0.1) #changed
g = g + theme_bw() + #new
theme(legend.position = "none") +
scale_radius(range = c(5 * size, 60 * size)) +
labs(x = "Centrality", y = "Density") +
xlim(xlimits) +
ylim(ylimits) +
theme(axis.text.x = element_blank(),
axis.ticks.x = element_blank(),
axis.text.y = element_blank(),
axis.ticks.y = element_blank(),
plot.background = element_blank(), #new
panel.grid = element_blank()) #new
g
dev.off() #stop pdf export
# 2016-2018 -----------------------------------------------------------------
#prepare values for plot
tm <- tmce3
size <- 0.8
meandens = mean(tm$clusters$rdensity)
meancentr = mean(tm$clusters$rcentrality)
rangex = max(c(meancentr - min(tm$clusters$rcentrality), max(tm$clusters$rcentrality) -
meancentr))
rangey = max(c(meandens - min(tm$clusters$rdensity), max(tm$clusters$rdensity) -
meandens))
xlimits = c(meancentr - rangex, meancentr + rangex)
ylimits = c(meandens - rangey, meandens + rangey)
# plot tmce1
#export pdf
pdf(file = "tmce3.pdf", width = 3.54331, height = 3.54331)
#ggplot
g = ggplot(tm$clusters, aes(x = tm$clusters$rcentrality, y = tm$clusters$rdensity, text = (tm$clusters$words))) +
geom_point(group = "NA", aes(size = log(as.numeric(tm$clusters$freq))),
shape = 20, col = adjustcolor(tm$clusters$color, alpha.f = 0.5))
g = g + geom_hline(yintercept = meandens, linetype = 2, size = 0.3, color = adjustcolor("black",alpha.f = 0.7)) +
geom_vline(xintercept = meancentr, linetype = 2, size = 0.3, color = adjustcolor("black", alpha.f = 0.7))
g = g + theme_bw() + #new
theme(legend.position = "none") +
scale_radius(range = c(5 * size, 60 * size)) +
labs(x = "Centrality", y = "Density") +
xlim(xlimits) +
ylim(ylimits) +
theme(axis.text.x = element_blank(),
axis.ticks.x = element_blank(),
axis.text.y = element_blank(),
axis.ticks.y = element_blank(),
plot.background = element_blank(), # new
panel.grid = element_blank()) # new
g = g + geom_label_repel(aes(group = "NA", label = ifelse(tm$clusters$freq > 1, unlist(tolower(tm$clusters$name)), "")),
size = 1.2 * (1 + size), angle = 0,
label.size = 0.1, # new
force = 2) # changed
g
dev.off() #stop pdf export
# 2019 -----------------------------------------------------------------
#prepare values for plot
tm <- tmce4
size <- 0.8
meandens = mean(tm$clusters$rdensity)
meancentr = mean(tm$clusters$rcentrality)
rangex = max(c(meancentr - min(tm$clusters$rcentrality), max(tm$clusters$rcentrality) -
meancentr))
rangey = max(c(meandens - min(tm$clusters$rdensity), max(tm$clusters$rdensity) -
meandens))
xlimits = c(meancentr - rangex, meancentr + rangex)
ylimits = c(meandens - rangey, meandens + rangey)
# plot tmce4
#export pdf
pdf(file = "tmce4.pdf", width = 3.54331, height = 3.54331)
#ggplot
g = ggplot(tm$clusters, aes(x = tm$clusters$rcentrality, y = tm$clusters$rdensity, text = (tm$clusters$words))) +
geom_point(group = "NA", aes(size = log(as.numeric(tm$clusters$freq))),
shape = 20, col = adjustcolor(tm$clusters$color, alpha.f = 0.5))
g = g + geom_hline(yintercept = meandens, linetype = 2, size = 0.3, color = adjustcolor("black",alpha.f = 0.7)) +
geom_vline(xintercept = meancentr, linetype = 2, size = 0.3, color = adjustcolor("black", alpha.f = 0.7))
g = g + theme_bw() + #new
theme(legend.position = "none") +
scale_radius(range = c(5 * size, 60 * size)) +
labs(x = "Centrality", y = "Density") +
xlim(xlimits) +
ylim(ylimits) +
theme(axis.text.x = element_blank(),
axis.ticks.x = element_blank(),
axis.text.y = element_blank(),
axis.ticks.y = element_blank(),
plot.background = element_blank(), #new
panel.grid = element_blank()) #new
g = g + geom_label_repel(aes(group = "NA", label = ifelse(tm$clusters$freq > 1, unlist(tolower(tm$clusters$name)), "")),
size = 1.2 * (1 + size), angle = 0,
label.size = 0.1, # changed
force = 3 ) # changed
g
dev.off() #stop pdf export