Potential switch to OpenAlex for retrieving references and cited by info

[emma-wilson]

Investigating the potential to use OpenAlex snowballing for citation chaser functions. Below code as a starting point, but output will need cleaning.

# Load libraries
library(openalexR)
library(ggraph)
library(tidygraph)

# Input DOI (1 or vector)
doi <- c("xxx", "xxx")

# Use OpenAlex to get the OpenAlex IDs for your DOIs
oaid <- oa_fetch(entity = "works", doi = doi, verbose = T)

# Select only the OpenAlex ID column as a vector
oaid <- oaid$id

# Remove prefix to just get OpenAlex ID
oaid <- gsub("https://openalex.org/", "", oaid)

# Get citations and cited by information from OpenAlex using vector of IDs
# In output:
# snowball_docs$nodes$id = the OpenAlex ID for each record
# snowball_docs$nodes$oa_input = TRUE/FALSE; T = ID refers to out of input IDs
# within snowball$edges... 
# for input IDs in "to" -> "from" is records which cite the input
# for input IDs in "from" -> "to" is records in the input record's reference list
snowball_docs <- oa_snowball(oaid, verbose = T)

# Create a graph
# As suggested on https://docs.ropensci.org/openalexR/#%EF%B8%8F-snowball-search
ggraph(graph = as_tbl_graph(snowball_docs), layout = "stress") +
  geom_edge_link(aes(alpha = after_stat(index)), show.legend = FALSE) +
  geom_node_point(aes(fill = oa_input, size = cited_by_count), shape = 21, color = "white") +
  geom_node_label(aes(filter = oa_input, label = id), nudge_y = 0.2, size = 3) +
  scale_edge_width(range = c(0.1, 1.5), guide = "none") +
  scale_size(range = c(3, 10), guide = "none") +
  scale_fill_manual(values = c("#a3ad62", "#d46780"), na.value = "grey", name = "") +
  theme_graph() +
  theme(
    plot.background = element_rect(fill = "transparent", colour = NA),
    panel.background = element_rect(fill = "transparent", colour = NA),
    legend.position = "bottom"
  ) +
  guides(fill = "none")