Word Clouds using Text Mining

December 19th, 2013

There was an interesting post on a blog which showed how straightforward it is to use the text mining tools (tm) from R along with the wordcloud package to create Word Clouds.

Following the example from this page I processed the text of the Golden Asse book (found at Project Guttenberg) to generate a word cloud.

aFile = readLines("goldenasse.txt")
 
library(tm)
myCorpus = Corpus(VectorSource(aFile))
 
myCorpus = tm_map(myCorpus, tolower)
myCorpus = tm_map(myCorpus, removePunctuation)
myCorpus = tm_map(myCorpus, removeNumbers)
myCorpus = tm_map(myCorpus, removeWords, stopwords("english"))
 
myDTM = TermDocumentMatrix(myCorpus, control = list(minWordLength = 1))
 
m = as.matrix(myDTM)
 
v = sort(rowSums(m), decreasing = TRUE)

The word cloud is simple to generate:

library(wordcloud)
set.seed(4363)
wordcloud(names(v), v, min.freq = 50)

and we get the following:

Word Cloud Example

Word Cloud Example

Comments are closed.

Statistics Books