One More PLoS Wordcloud

Data

The Public Library of Science (PLoS) is a nonprofit open-access science, technology, and medicine publisher. PLoS journals represent an extensive library of open-access journals and other scientific literature under an open-content license. The rplos package interacts with the PLoS journals and allows you to search and retrieve a wide variety of information from PLoS – no API key required!

Retrieve PLoS Titles

library(dplyr)
library(tm)
library(rplos)
#plosabstract searches the abstracts
#the fl command identifies what to retrieve
plos = plosabstract(q= "climate change", fl= "title", limit = 500)
head(plos)

$meta

$data

NA

#create a corpus of titles stripped of meaningless words
titleCorpus=with(plos, VCorpus(VectorSource(plos)))%>%
  tm_map(stripWhitespace)  %>%
  tm_map(removeNumbers)  %>%
  tm_map(removePunctuation)  %>%
  tm_map(content_transformer(tolower))  %>%
  tm_map(removeWords, stopwords("english"))

PLoS Climate Change Wordcloud

library(SnowballC)
library(wordcloud)
library(RColorBrewer)
wordcloud(titleCorpus, max.words = 50, scale = c(6, 1),
          colors=brewer.pal(3, "Set2"),random.order = FALSE)