R Notebook
Creating the environment
library(tidyverse)## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.1 ──## ✓ ggplot2 3.3.5 ✓ purrr 0.3.4
## ✓ tibble 3.1.6 ✓ dplyr 1.0.8
## ✓ tidyr 1.1.3 ✓ stringr 1.4.0
## ✓ readr 2.1.2 ✓ forcats 0.5.1## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()library(lubridate)##
## Attaching package: 'lubridate'## The following objects are masked from 'package:base':
##
## date, intersect, setdiff, unionlibrary(sjrdata)
library(igraph)##
## Attaching package: 'igraph'## The following objects are masked from 'package:lubridate':
##
## %--%, union## The following objects are masked from 'package:dplyr':
##
## as_data_frame, groups, union## The following objects are masked from 'package:purrr':
##
## compose, simplify## The following object is masked from 'package:tidyr':
##
## crossing## The following object is masked from 'package:tibble':
##
## as_data_frame## The following objects are masked from 'package:stats':
##
## decompose, spectrum## The following object is masked from 'package:base':
##
## unionlibrary(tidygraph)##
## Attaching package: 'tidygraph'## The following object is masked from 'package:igraph':
##
## groups## The following object is masked from 'package:stats':
##
## filterlibrary(ggraph)
library(bibliometrix)## To cite bibliometrix in publications, please use:
##
## Aria, M. & Cuccurullo, C. (2017) bibliometrix: An R-tool for comprehensive science mapping analysis,
## Journal of Informetrics, 11(4), pp 959-975, Elsevier.
##
##
## https://www.bibliometrix.org
##
##
## For information and bug reports:
## - Send an email to info@bibliometrix.org
## - Write a post on https://github.com/massimoaria/bibliometrix/issues
##
## Help us to keep Bibliometrix free to download and use by contributing with a small donation to support our research team (https://bibliometrix.org/donate.html)
##
##
## To start with the shiny web-interface, please digit:
## biblioshiny()Getting data
All data is here:
https://docs.google.com/spreadsheets/d/1nwszUhhHBzJS1WA0aP5lVMZY_lEVxjT4QO1l3bKiVtE/edit#gid=0
mzc_data <-
read_csv("https://docs.google.com/spreadsheets/d/1iwBM_RY391OVuuK1XrXJdtDoVLim1BBJ/export?format=csv&gid=1611166548") |>
filter(!is.na(ref_type))## Rows: 174 Columns: 30── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (24): name, full_name, subfield, AU, ID, C1, CR, JI, AB, RP, DT, DI, SN,...
## dbl (5): year, TC, PN, VL, PY
## lgl (1): AU_UN_NR
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.figure_1_data <-
read_csv("https://docs.google.com/spreadsheets/d/1nwszUhhHBzJS1WA0aP5lVMZY_lEVxjT4QO1l3bKiVtE/export?format=csv&gid=1442849006")## Rows: 49 Columns: 4── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## dbl (4): PY, wos, scopus, total
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.TC_all <-
read_csv("https://docs.google.com/spreadsheets/d/1nwszUhhHBzJS1WA0aP5lVMZY_lEVxjT4QO1l3bKiVtE/export?format=csv&gid=1467009091")## Rows: 49 Columns: 3── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## dbl (3): PY, TC_sum_all, TC_percentage
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.journal_df <-
read_csv("https://docs.google.com/spreadsheets/d/1nwszUhhHBzJS1WA0aP5lVMZY_lEVxjT4QO1l3bKiVtE/export?format=csv&gid=1871024023")## Rows: 351 Columns: 5── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (3): SR, JI_main, JI_ref
## dbl (2): PY_main, PY_ref
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.author_df <-
read_csv("https://docs.google.com/spreadsheets/d/1nwszUhhHBzJS1WA0aP5lVMZY_lEVxjT4QO1l3bKiVtE/export?format=csv&gid=640727835")## Rows: 6643 Columns: 3── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (2): from, to
## dbl (1): PY
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.Data Analysis
3.1 Scientific Production
figure_1a <-
figure_1_data |>
pivot_longer(!PY, names_to = "ref_type", values_to = "n") |>
filter(ref_type != "total") |>
ggplot(aes(x = factor(PY),
y = n,
fill = ref_type)) +
geom_bar(stat = "identity",
position = "dodge") +
geom_text(aes(label = n),
vjust = -0.3,
position = position_dodge(0.9),
size = 3,
family = "Times") +
scale_fill_manual(values = c("springgreen3",
"orange3")) +
theme(text = element_text(family = "Times",
face = "bold",
size =12),
panel.background = element_rect(fill = "white"),
legend.position = "bottom",
legend.title = element_text(size = 0),
axis.text.x = element_text(face = "bold",
angle = 45,
vjust = 0.5),
axis.line = element_line(color = "black",
size = 0.2)) +
labs(y = "Number of publications",
x = "Year")
figure_1a
Figure 1c - Citations
figure_1c <-
TC_all |>
ggplot(aes(x = PY , y = TC_sum_all)) +
geom_line(stat = "identity", color = "purple") +
geom_point(color = "purple") +
scale_x_continuous(breaks = seq(1974, year(today()) , by = 1)) +
geom_text(aes(label = TC_sum_all),
vjust = -0.3,
position = position_dodge(0.9),
size = 3,
family = "Times",
color = "purple") +
scale_fill_manual(values = c("springgreen3",
"orange3")) +
theme(text = element_text(family = "Times",
face = "bold",
size =12),
panel.background = element_rect(fill = "white"),
legend.position = "bottom",
legend.title = element_text(size = 0),
axis.text.x = element_text(face = "bold",
angle = 45,
vjust = 0.5),
axis.line = element_line(color = "black",
size = 0.2)) +
labs(y = "Number of citations",
x = "Year")
figure_1c
3.2 Country analysis
Table 2 - Country production
wos_scopus_countries <-
mzc_data |>
select(SR, AU_CO, TC) |>
separate_rows(AU_CO, sep = ";") |>
unique() |>
drop_na()
wos_scopus_countries_journals <-
wos_scopus_countries |>
left_join(mzc_data |>
select(SR, SO, PY),
by = "SR")
scimago_2020 <-
read_csv2("scimago2020.csv", show_col_types = FALSE) |>
select(SO = Title,
quartile = "SJR Best Quartile") |>
mutate(PY = 2020)## ℹ Using "','" as decimal and "'.'" as grouping mark. Use `read_delim()` for more control.scimago_2021 <-
read_csv2("scimago2020.csv", show_col_types = FALSE) |>
select(SO = Title,
quartile = "SJR Best Quartile") |>
mutate(PY = 2021)## ℹ Using "','" as decimal and "'.'" as grouping mark. Use `read_delim()` for more control.scimago_2020_2021 <-
scimago_2020 |>
bind_rows(scimago_2021) |>
select(PY, SO, quartile)
scimago <-
sjrdata::sjr_journals |>
select(PY = year,
SO = title,
quartile = sjr_best_quartile) |>
mutate(SO = str_to_upper(SO),
PY = as.numeric(PY)) |>
bind_rows(scimago_2020_2021)
wos_scopus_countries_journals_scimago <-
wos_scopus_countries_journals |>
left_join(scimago, by = c("PY", "SO")) |>
drop_na() |>
select(AU_CO, TC, quartile) |>
filter(quartile != "-")Table 2a - production
Production per country
table_2a <-
wos_scopus_countries |>
dplyr::select(AU_CO) |>
dplyr::group_by(AU_CO) |>
dplyr::summarise(count_co = n()) |>
dplyr::mutate(percentage_co = count_co / sum(count_co) * 100,
percentage_co = round(percentage_co, digits = 2)) |>
dplyr::arrange(desc(count_co))Table 2b - citations
Citations received per country
table_2b <-
wos_scopus_countries_journals_scimago |>
dplyr::select(AU_CO, TC) |>
dplyr::group_by(AU_CO) |>
dplyr::summarise(citation = sum(TC)) |>
dplyr::mutate(percentage_ci = citation / sum(citation) * 100) |>
dplyr::arrange(desc(citation))Table 2c - Quartiles
table_2c <-
wos_scopus_countries_journals_scimago |>
dplyr::select(AU_CO, quartile) |>
dplyr::group_by(AU_CO) |>
dplyr::count(quartile, sort = TRUE) |>
pivot_wider(names_from = quartile,
values_from = n) |>
dplyr::select(AU_CO, Q1, Q2, Q3, Q4) |>
dplyr::mutate(Q1 = replace_na(Q1, 0),
Q2 = replace_na(Q2, 0),
Q3 = replace_na(Q3, 0),
Q4 = replace_na(Q4, 0))Table 2 - Final
Merging all tables 2
table_2 <-
table_2a |>
left_join(table_2b, by = "AU_CO") |>
left_join(table_2c, by = "AU_CO") |>
mutate(percentage_ci = round(percentage_ci, digits = 2)) |>
slice(1:10)
table_2 |>
DT::datatable(class = "cell-border stripe",
rownames = F,
filter = "top",
editable = FALSE,
extensions = "Buttons",
options = list(dom = "Bfrtip",
buttons = c("copy",
"csv",
"excel",
"pdf",
"print")))Figure 2 - Country Collaboration
Exporting data to biblioshiny
# write.xlsx(x = wos_scopus_tos$df, file = "wos_scopus.xlsx")3.3 Journal Analysis
Table 3 Most productive scientific journals
table_1 <-
tibble(wos = length(mzc_data |>
select(ref_type) |>
filter(ref_type == "wos") |>
pull()), # Create a dataframe with the values.
scopus = length(mzc_data |>
select(ref_type) |>
filter(ref_type == "scopus") |>
pull()),
total = length(mzc_data$ref_type))
wos_journal <-
mzc_data |>
dplyr::filter(ref_type == "wos") |>
dplyr::select(journal = SO) |>
na.omit() |>
dplyr::count(journal, sort = TRUE) |>
dplyr::slice(1:20) |>
dplyr::rename(publications = n) |>
dplyr::mutate(database = "wos")
scopus_journal <-
mzc_data |>
filter(ref_type == "scopus") |>
dplyr::select(journal = SO) |>
na.omit() |>
dplyr::count(journal, sort = TRUE) |>
dplyr::slice(1:20) |>
dplyr::rename(publications = n) |>
dplyr::mutate(database = "scopus")
total_journal <-
mzc_data |>
dplyr::select(journal = SO) |>
na.omit() |>
dplyr::count(journal, sort = TRUE) |>
dplyr::slice(1:20) |>
dplyr::rename(publications = n) |>
dplyr::mutate(database = "total")
wos_scopus_total_journal <-
wos_journal |>
dplyr::bind_rows(scopus_journal,
total_journal) |>
pivot_wider(names_from = database,
values_from = publications) |>
dplyr::arrange(desc(total)) |>
dplyr::slice(1:10) |>
dplyr::mutate_all(~replace_na(., 0)) |>
dplyr::mutate(percentage = total / table_1 |>
dplyr::pull(total),
percentage = round(percentage, digits = 2))
wos_scopus_total_journal## # A tibble: 10 × 5
## journal wos scopus total percentage
## <chr> <dbl> <dbl> <dbl> <dbl>
## 1 COASTAL MANAGEMENT 3 22 25 0.2
## 2 OCEAN AND COASTAL MANAGEMENT 1 17 18 0.15
## 3 COASTAL ZONE MANAGEMENT JOURNAL 9 2 11 0.09
## 4 MARINE POLICY 2 7 9 0.07
## 5 JOURNAL OF THE AMERICAN PLANNING ASSOCIATION 0 7 7 0.06
## 6 INTERNATIONAL JOURNAL OF MARINE AND COASTAL LAW 1 5 6 0.05
## 7 ECOLOGY LAW QUARTERLY 1 2 3 0.02
## 8 COASTAL ZONE: PROCEEDINGS OF THE SYMPOSIUM ON … 2 0 2 0.02
## 9 CENTER FOR OCEANS LAW AND POLICY 0 2 2 0.02
## 10 OCEAN DEVELOPMENT AND INTERNATIONAL LAW 0 2 2 0.02Scopus Journal Citation Network
Creating the graph object
journal_citation_graph_weighted_tbl_small <-
journal_df |>
dplyr::select(JI_main, JI_ref) |>
dplyr::group_by(JI_main, JI_ref) |>
dplyr::count() |>
dplyr::rename(weight = n) |>
as_tbl_graph(directed = FALSE) |>
# convert(to_simple) |>
activate(nodes) |>
dplyr::mutate(components = tidygraph::group_components(type = "weak")) |>
dplyr::filter(components == 1) |>
activate(nodes) |>
dplyr::mutate(degree = centrality_degree(),
community = tidygraph::group_louvain()) |>
dplyr::select(-components) |>
dplyr::filter(degree >= 1)
# activate(edges) |>
# dplyr::filter(weight != 1)
communities <-
journal_citation_graph_weighted_tbl_small |>
activate(nodes) |>
data.frame() |>
dplyr::count(community, sort = TRUE) |>
dplyr::slice(1:10) |>
dplyr::select(community) |>
dplyr::pull()
# Filtering biggest communities
journal_citation_graph_weighted_tbl_small_fig <-
journal_citation_graph_weighted_tbl_small |>
activate(nodes) |>
dplyr::filter(community %in% communities)Figure 3 Journal Citation Network
Selecting nodes to show
jc_com_1 <-
journal_citation_graph_weighted_tbl_small_fig |>
activate(nodes) |>
dplyr::filter(community == communities[1]) |>
dplyr::mutate(degree = centrality_degree()) |>
dplyr::arrange(desc(degree)) |>
dplyr::slice(1:10) |>
data.frame() |>
dplyr::select(name)
jc_com_2 <-
journal_citation_graph_weighted_tbl_small_fig |>
activate(nodes) |>
dplyr::filter(community == communities[2]) |>
dplyr::mutate(degree = centrality_degree()) |>
dplyr::arrange(desc(degree)) |>
dplyr::slice(1:10) |>
data.frame() |>
dplyr::select(name)
jc_com_3 <-
journal_citation_graph_weighted_tbl_small_fig |>
activate(nodes) |>
dplyr::filter(community == communities[3]) |>
dplyr::mutate(degree = centrality_degree()) |>
dplyr::arrange(desc(degree)) |>
dplyr::slice(1:10) |>
data.frame() |>
dplyr::select(name)
jc_com_4 <-
journal_citation_graph_weighted_tbl_small_fig |>
activate(nodes) |>
dplyr::filter(community == communities[4]) |>
dplyr::mutate(degree = centrality_degree()) |>
dplyr::arrange(desc(degree)) |>
dplyr::slice(1:10) |>
data.frame() |>
dplyr::select(name)
jc_com_5 <-
journal_citation_graph_weighted_tbl_small_fig |>
activate(nodes) |>
dplyr::filter(community == communities[5]) |>
dplyr::mutate(degree = centrality_degree()) |>
dplyr::arrange(desc(degree)) |>
dplyr::slice(1:10) |>
data.frame() |>
dplyr::select(name)
jc_com_6 <-
journal_citation_graph_weighted_tbl_small_fig |>
activate(nodes) |>
dplyr::filter(community == communities[6]) |>
dplyr::mutate(degree = centrality_degree()) |>
dplyr::arrange(desc(degree)) |>
dplyr::slice(1:10) |>
data.frame() |>
dplyr::select(name)
jc_com_7<-
journal_citation_graph_weighted_tbl_small_fig |>
activate(nodes) |>
dplyr::filter(community == communities[7]) |>
dplyr::mutate(degree = centrality_degree()) |>
dplyr::arrange(desc(degree)) |>
dplyr::slice(1:10) |>
data.frame() |>
dplyr::select(name)
jc_com_8 <-
journal_citation_graph_weighted_tbl_small_fig |>
activate(nodes) |>
dplyr::filter(community == communities[8]) |>
dplyr::mutate(degree = centrality_degree()) |>
dplyr::arrange(desc(degree)) |>
dplyr::slice(1:10) |>
data.frame() |>
dplyr::select(name)
jc_com_9 <-
journal_citation_graph_weighted_tbl_small_fig |>
activate(nodes) |>
dplyr::filter(community == communities[9]) |>
dplyr::mutate(degree = centrality_degree()) |>
dplyr::arrange(desc(degree)) |>
dplyr::slice(1:10) |>
data.frame() |>
dplyr::select(name)
jc_com_10 <-
journal_citation_graph_weighted_tbl_small_fig |>
activate(nodes) |>
dplyr::filter(community == communities[10]) |>
dplyr::mutate(degree = centrality_degree()) |>
dplyr::arrange(desc(degree)) |>
dplyr::slice(1:10) |>
data.frame() |>
dplyr::select(name)
jc_com <-
jc_com_1 |>
bind_rows(jc_com_2,
jc_com_3,
# jc_com_4,
# jc_com_5,
# jc_com_6,
# jc_com_7,
# jc_com_8,
# jc_com_9,
# jc_com_10
)Figure 3a Journal Citation
figure_3a <-
journal_citation_graph_weighted_tbl_small_fig |>
activate(nodes) |>
dplyr::filter(name %in% jc_com$name) |>
dplyr::mutate(degree = centrality_degree(),
community = factor(community)) |>
dplyr::filter(degree != 0) |>
ggraph(layout = "graphopt") +
geom_edge_link(aes(width = weight),
colour = "lightgray") +
scale_edge_width(name = "Link strength") +
geom_node_point(aes(color = community,
size = degree)) +
geom_node_text(aes(label = name), repel = TRUE) +
scale_size(name = "Degree") +
# scale_color_binned(name = "Communities") +
theme_graph()
figure_3a
Figure 3b clusters
figure_3b <-
journal_citation_graph_weighted_tbl_small |>
activate(nodes) |>
data.frame() |>
dplyr::select(community) |>
dplyr::count(community, sort = TRUE) |>
dplyr::slice(1:10) |>
ggplot(aes(x = reorder(community, n), y = n)) +
geom_point(stat = "identity") +
geom_line(group = 1) +
# geom_text(label = as.numeric(community),
# nudge_x = 0.5,
# nudge_y = 0.5,
# check_overlap = T) +
labs(title = "Communities by size",
x = "communities",
y = "Journals") +
theme(text = element_text(color = "black",
face = "bold",
family = "Times New Roman"),
plot.title = element_text(size = 25),
panel.background = element_rect(fill = "white"),
axis.text.y = element_text(size = 15,
colour = "black"),
axis.text.x = element_text(size = 15,
colour = "black"),
axis.title.x = element_text(size = 20),
axis.title.y = element_text(size = 20))
figure_3b
3.1.4 Author Analysis
Table 4
data_biblio_wos <- biblioAnalysis(mzc_data |>
filter(ref_type == "wos") |>
data.frame())
wos_authors <-
data_biblio_wos$Authors |>
data.frame() |>
dplyr::rename(authors_wos = AU, papers_wos = Freq) |>
dplyr::arrange(desc(papers_wos)) |>
dplyr::slice(1:10) |>
dplyr::mutate(database_wos = "wos")
data_biblio_scopus <- biblioAnalysis(mzc_data |>
filter(ref_type == "scopus") |>
data.frame())
scopus_authors <-
data_biblio_scopus$Authors |>
data.frame() |>
dplyr::rename(authors_scopus = AU, papers_scopus = Freq) |>
dplyr::arrange(desc(papers_scopus)) |>
dplyr::slice(1:10) |>
dplyr::mutate(database_scopus = "scopus")
data_biblio_total <- biblioAnalysis(mzc_data)
total_authors <-
data_biblio_total$Authors |>
data.frame() |>
dplyr::rename(authors_total = AU,
papers_total = Freq) |>
dplyr::arrange(desc(papers_total)) |>
dplyr::slice(1:10) |>
dplyr::mutate(database_total = "total")
wos_scopus_authors <-
wos_authors |>
dplyr::bind_cols(scopus_authors,
total_authors)
wos_scopus_authors## authors_wos papers_wos database_wos authors_scopus papers_scopus
## 1 FELDMANN J 2 wos BOTERO C 3
## 2 ANDERSON S 1 wos FIDELMAN P 3
## 3 ARCHER J 1 wos FROHLICH M 3
## 4 BALCHAND A 1 wos GOOD J 3
## 5 BALDWIN C 1 wos HERSHMAN M 3
## 6 BECKMAN R 1 wos JACOBSON C 3
## 7 BELLAN G 1 wos O'HAGAN A 3
## 8 BELLAN-SANTINI D 1 wos SMITH T 3
## 9 BLATCH C 1 wos BALDWIN C 2
## 10 BOWEN R 1 wos BERND-COHEN T 2
## database_scopus authors_total papers_total database_total
## 1 scopus FIDELMAN P 4 total
## 2 scopus FROHLICH M 4 total
## 3 scopus HERSHMAN M 4 total
## 4 scopus JACOBSON C 4 total
## 5 scopus O'HAGAN A 4 total
## 6 scopus SMITH T 4 total
## 7 scopus BALDWIN C 3 total
## 8 scopus BOTERO C 3 total
## 9 scopus CARTER R 3 total
## 10 scopus GOOD J 3 totalCreating the ASN - graph object
author_network_time <-
author_df |>
tidygraph::as_tbl_graph(directed = FALSE) |>
activate(nodes) |>
# dplyr::mutate(components = tidygraph::group_components(type = "weak")) |>
# dplyr::filter(components == 1) |>
dplyr::mutate(degree = centrality_degree(),
community = as.factor(group_louvain()))
author_network <-
author_df |>
dplyr::select(-PY) |>
dplyr::group_by(from, to) |>
dplyr::count() |>
dplyr::rename(weight = n) |>
tidygraph::as_tbl_graph(directed = FALSE) |>
activate(nodes) |>
# dplyr::mutate(components = tidygraph::group_components(type = "weak")) |>
# dplyr::filter(components == 1) |>
dplyr::mutate(degree = centrality_degree(),
community = as.factor(group_louvain()))Figure 4a clusters of each community
figure_4a <-
author_network |>
activate(nodes) |>
data.frame() |>
dplyr::count(community) |>
slice(1:10) |>
ggplot(aes(x = reorder(community, n), y = n)) +
geom_point(stat = "identity") +
geom_line(group = 1) +
# geom_text(label = as.numeric(community),
# nudge_x = 0.5,
# nudge_y = 0.5,
# check_overlap = T) +
labs(title = "Communities by size",
x = "communities",
y = "Authors") +
theme(text = element_text(color = "black",
face = "bold",
family = "Times New Roman"),
plot.title = element_text(size = 25),
panel.background = element_rect(fill = "white"),
axis.text.y = element_text(size = 15,
colour = "black"),
axis.text.x = element_text(size = 15,
colour = "black"),
axis.title.x = element_text(size = 20),
axis.title.y = element_text(size = 20))
figure_4a
Figure 4b Longitudinal data of ASN
# Create a dataframe with links
fig_1c_edges <-
author_network_time |>
activate(edges) |>
as_tibble() |>
dplyr::select(year = PY) |>
dplyr::count(year) |>
dplyr::filter(year >= 2000,
year <= 2022) |>
dplyr::mutate(percentage = n/max(n)) |>
dplyr::select(year, percentage)
# Create a data frame with author and year
fig_1c_nodes <- # 21 row
author_network_time |>
activate(edges) |>
as_tibble() |>
dplyr::select(author = from,
year = PY) |>
bind_rows(author_network_time |>
activate(edges) |>
as_tibble() |>
dplyr::select(author = to,
year = PY)) |>
unique() |>
dplyr::group_by(author) |>
dplyr::slice(which.min(year)) |>
dplyr::ungroup() |>
dplyr::select(year) |>
dplyr::group_by(year) |>
dplyr::count(year) |>
dplyr::filter(year >= 2000,
year <= 2022) |>
dplyr::ungroup() |>
dplyr::mutate(percentage = n / max(n)) |>
select(year, percentage)plotting figure 4b
figure_4b <-
fig_1c_nodes |>
mutate(type = "nodes") |>
bind_rows(fig_1c_edges |>
mutate(type = "links")) |>
ggplot(aes(x = year,
y = percentage,
color = type)) +
geom_point() +
geom_line() +
theme(legend.position = "right",
text = element_text(color = "black",
face = "bold",
family = "Times New Roman"),
plot.title = element_text(size = 25),
panel.background = element_rect(fill = "white"),
axis.text.y = element_text(size = 15,
colour = "black"),
axis.text.x = element_text(size = 15,
colour = "black",
angle = 45, vjust = 0.5
),
axis.title.x = element_text(size = 20),
axis.title.y = element_text(size = 20),
legend.text = element_text(size = "15"),
legend.title = element_blank()) +
labs(title = "Nodes and links through time",
y = "Percentage") +
scale_y_continuous(labels = scales::percent) +
scale_x_continuous(breaks = seq(2000, 2021, by = 1))
figure_4b
Filtering only the top 10 nodes with best degree in the first 6 clusters.
asn_TM_connected_1 <-
author_network |>
activate(nodes) |>
dplyr::mutate(community = as.numeric(community)) |>
# filter(community >= 6) |>
dplyr::filter(community == 1) |>
# group_by(community) |>
dplyr::mutate(degree_community = centrality_degree()) |>
dplyr::arrange(desc(degree_community)) |>
dplyr::slice(1:10)
asn_TM_connected_2 <-
author_network |>
activate(nodes) |>
dplyr::mutate(community = as.numeric(community)) |>
# filter(community >= 6) |>
dplyr::filter(community == 2) |>
# group_by(community) |>
dplyr::mutate(degree_community = centrality_degree()) |>
dplyr::arrange(desc(degree_community))|>
dplyr::slice(1:10)
asn_TM_connected_3 <-
author_network |>
activate(nodes) |>
dplyr::mutate(community = as.numeric(community)) |>
# filter(community >= 6) |>
dplyr::filter(community == 3) |>
# group_by(community) |>
dplyr::mutate(degree_community = centrality_degree()) |>
dplyr::arrange(desc(degree_community)) |>
dplyr::slice(1:10)
asn_TM_connected_4 <-
author_network |>
activate(nodes) |>
dplyr::mutate(community = as.numeric(community)) |>
# filter(community >= 6) |>
dplyr::filter(community == 4) |>
# group_by(community) |>
dplyr::mutate(degree_community = centrality_degree()) |>
dplyr::arrange(desc(degree_community)) |>
dplyr::slice(1:10)
asn_TM_connected_5 <-
author_network |>
activate(nodes) |>
dplyr::mutate(community = as.numeric(community)) |>
# filter(community >= 6) |>
dplyr::filter(community == 5) |>
# group_by(community) |>
dplyr::mutate(degree_community = centrality_degree()) |>
dplyr::arrange(desc(degree_community)) |>
dplyr::slice(1:10)
asn_TM_connected_6 <-
author_network |>
activate(nodes) |>
dplyr::mutate(community = as.numeric(community)) |>
# filter(community >= 6) |>
dplyr::filter(community == 6) |>
# group_by(community) |>
dplyr::mutate(degree_community = centrality_degree()) |>
dplyr::arrange(desc(degree_community)) |>
dplyr::slice(1:10)
asn_TM_connected_7 <-
author_network |>
activate(nodes) |>
dplyr::mutate(community = as.numeric(community)) |>
# filter(community >= 6) |>
dplyr::filter(community == 7) |>
# group_by(community) |>
dplyr::mutate(degree_community = centrality_degree()) |>
dplyr::arrange(desc(degree_community)) |>
dplyr::slice(1:10)Saving the nodes we’re gonna show
nodes_community_1 <-
asn_TM_connected_1 |>
activate(nodes) |>
as_tibble() |>
dplyr::select(name)
nodes_community_2 <-
asn_TM_connected_2 |>
activate(nodes) |>
as_tibble() |>
dplyr::select(name)
nodes_community_3 <-
asn_TM_connected_3 |>
activate(nodes) |>
as_tibble() |>
dplyr::select(name)
nodes_community_4 <-
asn_TM_connected_4 |>
activate(nodes) |>
as_tibble() |>
dplyr::select(name)
nodes_community_5 <-
asn_TM_connected_5 |>
activate(nodes) |>
as_tibble() |>
dplyr::select(name)
nodes_community_6 <-
asn_TM_connected_6 |>
activate(nodes) |>
as_tibble() |>
dplyr::select(name)
nodes_community_7 <-
asn_TM_connected_7 |>
activate(nodes) |>
as_tibble() |>
dplyr::select(name)
nodes_selected_10 <-
nodes_community_1 |>
bind_rows(nodes_community_2,
nodes_community_3
# nodes_community_4,
# nodes_community_5,
# nodes_community_6,
# nodes_community_7
)Filtering selected nodes
asn_selected_nodes <-
author_network |>
activate(nodes) |>
dplyr::filter(name %in% nodes_selected_10$name)
# dplyr::mutate(final_plot = tidygraph::group_components(type = "weak"))
# dplyr::filter(final_plot == 1)Ploting the selected network
figure_4c <-
asn_selected_nodes |>
activate(nodes) |>
dplyr::mutate(degree = centrality_degree()) |>
ggraph(layout = "graphopt") +
geom_edge_link(colour = "lightgray",
aes(width = weight)) +
geom_node_point(aes(color = community,
size = degree)) +
geom_node_text(aes(label = name), repel = TRUE) +
theme_graph()
figure_4c