R Notebook

rm(list = ls())

Sys.setenv(LANG = "en")
library(xlsx)
library(readr)
library(readxl)
library(tidyverse)
library(stringr)
library(stringi)
library(gghighlight)
library(countrycode)
library(countries)
library(janitor)
library(sf)

library(janitor)
library(sf)
library(ggthemes)
library(here)
library(viridis)
library(ggplot2)
library(formatR)
library(gtools)
library(nnet) 
library(patchwork)
library(ggh4x)

library(plm)
library(broom)
library(ggalluvial)

library(pals)

Load data —————————————————————

Large datasets (move load to different notebook)

aggregates <- read_csv("../aggregated_data/aggregates.csv")
aggregates_year <- read_csv("../aggregated_data/aggregates_year.csv")

Convert vars to factor. read_csv changes original type.

aggregates_year <- aggregates_year %>% 
  mutate(subregion_rf = as_factor(subregion),
        subregion_rf = relevel(subregion_rf, "Northern America"),
        continent = as_factor(continent),
        continent = relevel(continent, "Americas"))

Figure 3

Continent by year

myColors <- alphabet2()
names(myColors) <- levels(aggregates_year$subregion_rf)

(salience_subregions <- aggregates_year %>%
    filter(!is.na(subregion_rf)) %>% 
    group_by(pubyear, continent, subregion_rf) %>% 
    summarise(n = sum(art_country_y)) %>% 
    ggplot() +
    geom_bar(mapping = aes(x = pubyear, y = n, group = subregion_rf, fill = subregion_rf), stat = "identity") +
    facet_wrap(vars(continent)) +
  theme_minimal() +
  theme(legend.title = element_blank(),
        legend.text = element_text(size = 22),
        legend.position = "bottom",
        axis.text = element_text(size = 25),
        axis.title=element_text(size = 25),
        strip.text = element_text(size = 25)) +
    labs(fill = "Subregion UN classification",
         y = "Research salience",
         x = "Publication year") +
  scale_fill_manual(name = "subregion_rf", values = myColors))

ggsave("../output_figures/subregions_year_abs.png", width = 50, height = 30, units = "cm", dpi = 700, scale = 1, plot = last_plot())

Figure S. 3

Underrepresentation by continent, subregion, and year

(repr_subregions <- aggregates_year %>%
    filter(!is.na(subregion_rf)) %>%
    count(continent, subregion_rf, pubyear, repr_y_s) %>% 
    filter(repr_y_s == "Under") %>% 
    ggplot() +
    geom_bar(mapping = aes(x = pubyear, y = n, group = subregion_rf, fill = subregion_rf), stat = "identity") +
    facet_wrap(vars(continent)) +
  theme_minimal() +
  theme(legend.title = element_blank(),
        legend.text = element_text(size = 22),
        legend.position = "bottom",
        axis.text = element_text(size = 25),
        axis.title=element_text(size = 25),
        strip.text = element_text(size = 25)) +
    labs(fill = "Subregion UN classification",
         y = "Counts of under-rerepresented countries",
         x = "Publication year") +
  scale_fill_manual(name = "subregion_rf", values = myColors))

ggsave("../output_figures/representation_subregions_year_abs.png", width = 50, height = 30, units = "cm", dpi = 700, scale = 1, plot = last_plot())

(repr_subregions <- aggregates_year %>%
    filter(!is.na(subregion_rf)) %>%
    count(continent, subregion_rf, pubyear, repr_y_s) %>% 
    filter(repr_y_s == "Under") %>% 
    ggplot() +
    geom_bar(mapping = aes(x = pubyear, y = n, group = subregion_rf, fill = subregion_rf), stat = "identity") +
    facet_wrap(vars(continent)) +
  theme_minimal() +
  theme(legend.position = "none",
        axis.text = element_text(size = 25),
        axis.title=element_text(size = 25),
        strip.text = element_text(size = 25)) +
    labs(fill = "Subregion UN classification",
         y = "Counts of under-rerepresented countries",
         x = "Publication year") +
  scale_fill_manual(name = "subregion_rf", values = myColors))

salience_subregions / repr_subregions

ggsave("../output_figures/subregions_both.png", width = 50, height = 60, units = "cm", dpi = 700, scale = 1, plot = last_plot())