Creating a wordcloud using R!

Overview

Wordclouds can be a great way to identify recurring themes in documents.

Wordcloud tutorial

First you need to load the relevant libraries.

library(pdftools)
library(wordcloud)
library(RColorBrewer)
library(wordcloud2)
library(tm)
library(dplyr)

Then you tell R where the folder with the PDFs you want to use are located.

files <- list.files("/Users/denaclink/Desktop/RStudio Projects/Dena-Clink-Website/Clink Publications ",full.names = T)

We then use the ‘Corpus’ function to extract text from the PDF documents.

corp <- Corpus(URISource(files),
               readerControl = list(reader = readPDF))
print(corp)

We can then create a document-term matrix that describes the frequency of terms that occur in the documents.

publications.tdm <- TermDocumentMatrix(corp, 
                                   control = 
                                     list(removePunctuation = TRUE,
                                          stopwords = TRUE,
                                          tolower = TRUE,
                                          stemming = TRUE,
                                          removeNumbers = TRUE,
                                          bounds = list(global = c(3, Inf)))) 

We can then do some data processing to prepare to input the document-term matrix to the wordcloud.

# Convert the output to a matrix
matrix <- as.matrix(publications.tdm) 
head(matrix)

# We then count the frequency of the use of different words
words <- sort(rowSums(matrix),decreasing=TRUE) 
head(words)

# Convert that output to a dataframe
df <- data.frame(word = names(words),freq=words)

# Remove words that we don't want to include in the wordcloud
remove.rows <- which(df$word %in% c('clink','use','includ') )
df <- df[- remove.rows,]

Then we use the ‘wordcloud’ function to create our wordcloud!

wordcloud(words = df$word, freq = df$freq, min.freq = 4,           
          max.words=200, random.order=FALSE, rot.per=0.35,            
          colors=brewer.pal(8, "Dark2"))