Scientometric Analysis

Creating the environment

library(conflicted)

## Warning: package 'conflicted' was built under R version 4.4.3

library(tidyverse)

## Warning: package 'tidyverse' was built under R version 4.4.3

## Warning: package 'ggplot2' was built under R version 4.4.3

## Warning: package 'tibble' was built under R version 4.4.3

## Warning: package 'tidyr' was built under R version 4.4.3

## Warning: package 'readr' was built under R version 4.4.3

## Warning: package 'purrr' was built under R version 4.4.3

## Warning: package 'dplyr' was built under R version 4.4.3

## Warning: package 'stringr' was built under R version 4.4.2

## Warning: package 'forcats' was built under R version 4.4.3

## Warning: package 'lubridate' was built under R version 4.4.3

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ ggplot2   3.5.1     ✔ tibble    3.2.1
## ✔ lubridate 1.9.4     ✔ tidyr     1.3.1
## ✔ purrr     1.0.4

library(tidygraph)

## Warning: package 'tidygraph' was built under R version 4.4.3

library(igraph)

## Warning: package 'igraph' was built under R version 4.4.3

library(ggplot2)
library(bibliometrix)

## Warning: package 'bibliometrix' was built under R version 4.4.3

## Please note that our software is open source and available for use, distributed under the MIT license.
## When it is used in a publication, we ask that authors properly cite the following reference:
## 
## Aria, M. & Cuccurullo, C. (2017) bibliometrix: An R-tool for comprehensive science mapping analysis, 
##                         Journal of Informetrics, 11(4), pp 959-975, Elsevier.
## 
## Failure to properly cite the software is considered a violation of the license.
##                         
## For information and bug reports:
##                         - Take a look at https://www.bibliometrix.org
##                         - Send an email to info@bibliometrix.org   
##                         - Write a post on https://github.com/massimoaria/bibliometrix/issues
##                         
## Help us to keep Bibliometrix and Biblioshiny 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 Biblioshiny app, please digit:
## biblioshiny()

library(tosr)

## Warning: package 'tosr' was built under R version 4.4.3

library(here)

## Warning: package 'here' was built under R version 4.4.3

## here() starts at C:/Users/user/Documents/AR_SMG

library(lubridate)
#library(sjrdata)
library(openxlsx)

## Warning: package 'openxlsx' was built under R version 4.4.3

library(zoo)

## Warning: package 'zoo' was built under R version 4.4.3

library(RSQLite)

## Warning: package 'RSQLite' was built under R version 4.4.3

library(plyr)

## Warning: package 'plyr' was built under R version 4.4.3

## ------------------------------------------------------------------------------
## You have loaded plyr after dplyr - this is likely to cause problems.
## If you need functions from both plyr and dplyr, please load plyr first, then dplyr:
## library(plyr); library(dplyr)
## ------------------------------------------------------------------------------

library(dplyr)
library(journalabbr)

## Warning: package 'journalabbr' was built under R version 4.4.3

library(ggraph)

## Warning: package 'ggraph' was built under R version 4.4.3

library(XML)

## Warning: package 'XML' was built under R version 4.4.2

library(readxl)

## Warning: package 'readxl' was built under R version 4.4.3

library(svglite)

## Warning: package 'svglite' was built under R version 4.4.3

source("verbs.R")
giant.component <- function(graph) {
  cl <- igraph::clusters(graph)
  igraph::induced.subgraph(graph, 
                           which(cl$membership == which.max(cl$csize)))
}

Data getting

Summary of WoS and Scopus

table_1 <- 
  tibble(wos = length(wos$AU), # Create a dataframe with the values.
         scopus = length(scopus$AU), 
         total = length(wos_scopus$AU))
table_1 %>% 
  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")))

wos_scopus %>% 
  tidyr::separate_rows(DT, sep = ";") %>% 
  dplyr::count(DT, sort = TRUE)%>% 
  dplyr::mutate(percentage = n /sum(n),
                percentage = percentage * 100,
                percentage = round(percentage, digits = 2)) %>%
  dplyr::rename(total = n) %>% 
  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")))

Resutls

Scientometric Analysis

3.1 Scientific Production

Figure 1a - Scopus + WoS

Combine charts using Python Matplotlib & Reticulate

library(reticulate)
numpy <- import("numpy")
matplotlib <- import("matplotlib")

year_start <- 2002
year_end <- 2024
years_full <- seq(year_start, year_end)
years_missing <- setdiff(years_full, figure_1_data$PY)

for (year in years_missing) {
  total_wos <- wos %>% dplyr::filter(PY == year) %>% nrow()
  total_scopus <- scopus %>% dplyr::filter(PY == year) %>% nrow()
  total_wos_scopus <- wos_scopus %>% dplyr::filter(PY == year) %>% nrow()
  new_row <- data.frame(PY = year, total = total_wos_scopus, scopus = total_scopus, wos = total_wos)
  figure_1_data <- dplyr::bind_rows(figure_1_data, new_row)
}

figure_1_data <- figure_1_data %>% dplyr::arrange(desc(PY))

TC_all <- data.frame(PY = integer(), TC_sum_all = numeric(), TC_percentage = numeric())

for (year in years_full) {
  ncitas_wos <- wos %>% dplyr::filter(PY == year) %>% dplyr::summarize(sum(TC, na.rm = TRUE)) %>% dplyr::pull()
  ncitas_scopus <- scopus %>% dplyr::filter(PY == year) %>% dplyr::summarize(sum(TC, na.rm = TRUE)) %>% dplyr::pull()
  ncitas <- ncitas_wos + ncitas_scopus
  new_row_tc <- data.frame(PY = year, TC_sum_all = ncitas, TC_percentage = NA)
  TC_all <- dplyr::bind_rows(TC_all, new_row_tc)
}

total_citas <- sum(TC_all$TC_sum_all, na.rm = TRUE)

TC_all <- TC_all %>% dplyr::mutate(TC_percentage = round(TC_sum_all / total_citas * 100, 2))
TC_all <- TC_all %>% dplyr::arrange(desc(PY))
TC_all$TC_sum_all <- as.integer(TC_all$TC_sum_all)

import matplotlib.pyplot as plt
# from matplotlib.ticker import FuncFormatter
def clean_integer_formatter(x, pos):
    return '{:d}'.format(int(x))
fig, ax = plt.subplots(figsize=(11, 7.5))
ax.plot(tpx, tpy, color='r', marker='o', label='Total Publications')
ax.set_xlabel('Year', fontsize=20)
ax.set_ylabel('Total Publications', color='r', fontsize=20)
barw = 0.5
ax.bar(sx, sy, color='g', label='Scopus', alpha=0.5, width=barw)
ax.bar(wx1, wy, color='orange', label='WoS', alpha=0.8, width=barw)
twin_axes = ax.twinx()
twin_axes.plot(tcx, tcy, color='purple', marker='o', label='Total Citations')
twin_axes.set_ylabel('Total Citations', color='purple', fontsize=20)
plt.title('Total Scientific Production vs. Total Citations', fontsize=23)
plt.legend(loc='center left', fontsize=15)
ax.grid(False)
ax.legend(loc='upper left', fontsize=15)
twin_axes.set_ylim(0, max(tcy)+100)

## (0.0, 5796.0)

for i, label in enumerate(tcy):
    twin_axes.annotate(label, (tcx[i], tcy[i] + 0.5), color='purple', size=13)
for i, label in enumerate(tpy):
    ax.annotate(label, (tpx[i], tpy[i] + 0.8), color='red', size=13)
for i, label in enumerate(wy):
    ax.annotate(label, (wx1[i], wy[i] + 0.1), color='brown', size=13)
for i, label in enumerate(sy):
    ax.annotate(label, (sx[i], sy[i] + 0.2), color='green', size=13)
ax.set_xticks(tpx)
ax.set_xticklabels([int(year) for year in tpx], fontsize=14, rotation=75)
# ax.yaxis.set_major_formatter(FuncFormatter(clean_integer_formatter))
# twin_axes.yaxis.set_major_formatter(FuncFormatter(clean_integer_formatter))
ax.tick_params(axis='y', labelsize=15)
twin_axes.tick_params(axis='y', labelsize=15)
plt.savefig("./f1/figura_1.svg")
plt.show()

3.2 Country analysis

Table 2 - Country production

table_2_country |>
  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 2a - Country Collaboration

figure_2a <- 
  figure_2_country_wos_scopus_1 |>
  activate(edges) |> 
  # tidygraph::rename(weight = n) |> 
  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_2a

ggsave("./figura_dos/figura_2a.svg", 
       plot = figure_2a, 
       device = "svg")

Figure 2b Clusters

library(svglite)
figure_2b <- 
  figure_2_country_wos_scopus_1 |> 
  activate(nodes) |> 
  data.frame() |> 
  group_by(community) |> 
  dplyr::count(community, sort = TRUE) |> 
  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 = "Countries") +
  theme(text = element_text(color = "black",
                            face = "bold",
                            family = "Times"),
        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_2b

ggsave("./figura_dos/figura_2b.svg", 
       plot = figure_2b, 
       device = "svg")

Figure 2c Longitudinal

# Create a dataframe with links 
figure_2c_edges <- 
  figure_2_country_wos_scopus |>
  dplyr::filter(from != to) |> 
  tidygraph::as_tbl_graph() |> 
  activate(edges) |> 
  as_tibble() |> 
  dplyr::select(year = PY) |> 
  dplyr::count(year) |> 
  dplyr::filter(year >= year_start,
                year <= year_end) |> 
  dplyr::mutate(percentage = n/max(n)) |> 
  dplyr::select(year, percentage)
# Create a data frame with author and year 
figure_2c_nodes <- # 21 row 
  figure_2_country_wos_scopus |>
  dplyr::filter(from != to) |> 
  tidygraph::as_tbl_graph() |> 
  activate(edges) |> 
  as_tibble() |> 
  dplyr::select(CO = from, 
                year = PY) |>
  bind_rows(figure_2_country_wos_scopus |>  
              tidygraph::as_tbl_graph() |> 
              tidygraph::activate(edges) |> 
              tidygraph::as_tibble() |> 
              dplyr::select(CO = to, 
                            year = PY)) |> 
  unique() |> 
  dplyr::group_by(CO) |> 
  dplyr::slice(which.min(year)) |>
  dplyr::ungroup() |> 
  dplyr::select(year) |> 
  dplyr::group_by(year) |> 
  dplyr::count(year) |> 
  dplyr::filter(year >= year_start,
                year <= year_end) |> 
  dplyr::ungroup() |> 
  dplyr::mutate(percentage = n / max(n)) |> 
  select(year, percentage)

figure_2c <- 
  figure_2c_nodes |> 
  dplyr::mutate(type = "nodes",
         year = as.numeric(year)) |> 
  bind_rows(figure_2c_edges |> 
              dplyr::mutate(type = "links",
                     year = as.numeric(year))) |> 
  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"),
        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(year_start, year_end, by = 1))

figure_2c

ggsave("./figura_dos/figura_2c.svg", 
       plot = figure_2c, 
       device = "svg")

3.3 Journal Analysis

Table 3 Most productive journals

library(dplyr)
library(stringr)

journals_sorted <- table_3_journal %>%
  dplyr::arrange(desc(total)) %>%
  head(10)
journals_sorted <- journals_sorted %>%
  dplyr::mutate(journal = tolower(journal))
names_journals <- journals_sorted$journal
colnames(journals_sorted) <- c("SO", "wos", "scopus", "total", "percentage")
wos_scopus_sn <- wos_scopus %>%
  select(SO, SN) %>%
  dplyr::mutate(SO = tolower(SO))
wos_scopus_sn <- wos_scopus_sn %>%
  dplyr::filter(SO %in% names_journals) %>%
  distinct(SO, .keep_all = TRUE)
tabla_apariciones <- merge(wos_scopus_sn, journals_sorted, by = "SO", all.x = TRUE)

dataa <- data_scimago %>%
  dplyr::mutate(
    Issn = str_split(Issn, ",") %>%
      lapply(function(x) toupper(str_trim(x))),
    Title = tolower(Title),
    SJR = if_else(is.na(SJR), "--", as.character(SJR)),
    QUARTIL = if_else(is.na(QUARTIL), "--", as.character(QUARTIL)),
    `H index` = if_else(is.na(`H.index`), "--", as.character(`H.index`))
  )
resultados <- list()
for (i in 1:nrow(tabla_apariciones)) {
  row <- tabla_apariciones[i, ]
  sn <- tolower(gsub("-", "", as.character(row$SN)))
  nombre_revista <- row$SO
  wos <- row$wos
  scopus <- row$scopus
  total <- row$total

  coincidencias <- dataa %>%
    dplyr::filter(sapply(Issn, function(x) sn %in% x))

  if (nrow(coincidencias) > 0) {
    for (j in 1:nrow(coincidencias)) {
      match <- coincidencias[j, ]
      resultados <- append(resultados, list(data.frame(
        Nombre_Revista = nombre_revista,
        SN = sn,
        WOS = wos,
        SCOPUS = scopus,
        Total = total,
        `Impact factor` = match$SJR,
        QUARTIL = match$QUARTIL,
        `H index` = match$`H index`
      )))
    }
  } else {
    coincidencias_nombre <- dataa %>%
      dplyr::filter(Title == nombre_revista)

    if (nrow(coincidencias_nombre) > 0) {
      for (j in 1:nrow(coincidencias_nombre)) {
        match <- coincidencias_nombre[j, ]
        resultados <- append(resultados, list(data.frame(
          Nombre_Revista = nombre_revista,
          SN = sn,
          WOS = wos,
          SCOPUS = scopus,
          Total = total,
          `Impact factor` = match$SJR,
          QUARTIL = match$QUARTIL,
          `H index` = match$`H index`
        )))
      }
    } else {
      resultados <- append(resultados, list(data.frame(
        Nombre_Revista = nombre_revista,
        SN = sn,
        WOS = wos,
        SCOPUS = scopus,
        Total = total,
        `Impact factor` = "--",
        QUARTIL = "--",
        `H index` = "--"
      )))
    }
  }
}
df_resultado <- do.call(rbind, resultados) 
# Convertir la lista de resultados a un data frame y ordenarlo por "Total" en orden descendente
df_resultado <- df_resultado %>%
  dplyr::mutate(Nombre_Revista = str_to_title(Nombre_Revista)) %>%
  dplyr::arrange(desc(Total))

DT::datatable(df_resultado, 
              class = "cell-border stripe", 
              rownames = FALSE, 
              filter = "top", 
              editable = FALSE, 
              extensions = "Buttons", 
              options = list(dom = "Bfrtip",
                             buttons = c("copy", "csv", "excel", "pdf", "print")))

Figure 3 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)

Selecting nodes to show

figure_3a_1 <- 
  SO_edges %>% 
  tidygraph::as_tbl_graph() %>% 
  tidygraph::activate(nodes) %>%
  tidygraph::mutate(id = SO_nodes$id) %>% 
  tidygraph::left_join(SO_nodes) %>% 
  tidygraph::select(-id) %>% 
  tidygraph::rename(name = Label) %>% 
  ggraph(layout = "graphopt") +
  geom_edge_link(aes(width = weight), colour = "lightgray") +
  scale_edge_width(name = "Link strength") +
  geom_node_point(aes(color = as.factor(community), size = degree)) +
  geom_node_text(aes(label = name), repel = TRUE) +
  scale_size(name = "Degree") +
  scale_color_discrete(name = "Communities") +  # Cambié scale_color_binned a scale_color_discrete
  theme_graph()

figure_3a_1

ggsave("./figura_tres/figura_3a_1.svg", 
       plot = figure_3a_1, 
       device = "svg")

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"),
        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

ggsave("./figura_tres/figura_3b.svg", 
       plot = figure_3b, 
       device = "svg")

Figure 3c Longitudinal

# Create a dataframe with links 
figure_3c_edges <- 
  journal_df |>
  select(from = JI_main, to = JI_ref, PY = PY_ref) %>% 
  dplyr::filter(from != to) |> 
  tidygraph::as_tbl_graph() |> 
  activate(edges) |> 
  as_tibble() |> 
  dplyr::select(year = PY) |> 
  dplyr::count(year) |> 
  dplyr::filter(year >= year_start,
                year <= year_end) |> 
  dplyr::mutate(percentage = n/max(n)) |> 
  dplyr::select(year, percentage)
# Create a data frame with author and year 
figure_3c_nodes <- # 21 row 
  journal_df |>
  select(from = JI_main, to = JI_ref, PY = PY_ref) %>% 
  dplyr::filter(from != to) |> 
  tidygraph::as_tbl_graph() |> 
  activate(edges) |> 
  as_tibble() |> 
  dplyr::select(CO = from, 
                year = PY) |>
  bind_rows(journal_df |>
              select(from = JI_main, 
                     to = JI_ref, 
                     PY = PY_ref) %>%  
              tidygraph::as_tbl_graph() |> 
              tidygraph::activate(edges) |> 
              tidygraph::as_tibble() |> 
              dplyr::select(CO = to, 
                            year = PY)) |> 
  unique() |> 
  dplyr::group_by(CO) |> 
  dplyr::slice(which.min(year)) |>
  dplyr::ungroup() |> 
  dplyr::select(year) |> 
  dplyr::group_by(year) |> 
  dplyr::count(year) |> 
  dplyr::filter(year >= year_start,
                year <= year_end) |> 
  dplyr::ungroup() |> 
  dplyr::mutate(percentage = n / max(n)) |> 
  select(year, percentage)

plotting figure 3b

figure_3c <- 
  figure_3c_nodes |> 
  dplyr::mutate(type = "nodes") |> 
  bind_rows(figure_3c_edges |> 
              dplyr::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"),
        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 = 60, 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(year_start, year_end, by = 1))

figure_3c

ggsave("./figura_tres/figura_3c.svg", 
       plot = figure_3c, 
       device = "svg")

3.4 Author Analysis

Table 4

table_4_authors |> 
  dplyr::select(authors_total, papers_total) %>% 
  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")))

Creating 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

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"),
        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

ggsave("./figura_cuatro/figura_4a.svg", 
       plot = figure_4a, 
       device = "svg")

Figure 4b Longitudinal

# 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 >= year_start,
                year <= year_end) |> 
  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 >= year_start,
                year <= year_end) |> 
  dplyr::ungroup() |> 
  dplyr::mutate(percentage = n / max(n)) |> 
  select(year, percentage)

plotting figure 4b

figure_4b <- 
  fig_1c_nodes |> 
  dplyr::mutate(type = "nodes") |> 
  bind_rows(fig_1c_edges |> 
              dplyr::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"),
        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(year_start, year_end, by = 1))

figure_4b

ggsave("./figura_cuatro/figura_4b.svg", 
       plot = figure_4b, 
       device = "svg")

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)

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_selected_10 <- 
  nodes_community_1 |> 
  bind_rows(nodes_community_2, 
            nodes_community_3,
            # nodes_community_4,
            # nodes_community_5,
            # nodes_community_6
  )

Filtering selected nodes

asn_selected_nodes <- 
  author_network |> 
  activate(nodes) |> 
  dplyr::filter(name %in% nodes_selected_10$name)  |> 
  dplyr::mutate(degree = centrality_degree())

# dplyr::mutate(final_plot = tidygraph::group_components(type = "weak")) |> 
# dplyr::filter(final_plot == 1)

Tree of Science

tos %>% 
  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")))

egos  <- 
  AU_ego_edges %>%
  tidygraph::as_tbl_graph() %>% 
  tidygraph::activate(nodes) %>%
  tidygraph::mutate(id = AU_ego_nodes$id) %>%
  dplyr::left_join(AU_ego_nodes %>% 
                     tidygraph::mutate(id = as.character(id))) %>% 
  dplyr::mutate(component = as.character(component))

## Joining with `by = join_by(id)`

egos |>
  ggraph(layout = "graphopt") +
  geom_edge_link(aes(width = weight),
                 colour = "lightgray") +
  scale_edge_width(name = "Link strength") +
  geom_node_point(aes(color = component, 
                      size = degree)) +
  geom_node_text(aes(label = Label), repel = TRUE) +
  scale_size(name = "Degree") +
  # scale_color_binned(name = "Communities") +
  theme_graph()

## Warning: ggrepel: 569 unlabeled data points (too many overlaps). Consider
## increasing max.overlaps

ggsave("./figura_cuatro/egos_network.svg", device = "svg")

## Saving 7 x 5 in image

## Warning: ggrepel: 566 unlabeled data points (too many overlaps). Consider
## increasing max.overlaps

Figure 4c Author Network

figure_4c <- 
  asn_selected_nodes |> 
  ggraph(layout = "graphopt") +
  geom_edge_link(width = 1, 
                 colour = "lightgray") +
  geom_node_point(aes(color = community, 
                      size = degree)) +
  geom_node_text(aes(label = name), repel = TRUE) +
  theme_graph()

figure_4c

ggsave("./figura_cuatro/figura_4c.svg", 
       plot = figure_4c, 
       device = "svg")