Simple.R

library(twitteR)
library(tm)
library(wordcloud)
library(RColorBrewer)


#necessary file for Windows
download.file(url="http://curl.haxx.se/ca/cacert.pem", destfile="cacert.pem")

#to get your consumerKey and consumerSecret see the twitteR documentation for instructions
consumer_key <- 'your consumerKey here'
consumer_secret <- 'your consumer secret here'
access_token <- 'your access token here'
access_secret <- 'you access secret here'
setup_twitter_oauth(consumer_key,consumer_secret,access_token,access_secret)

mach_tweets = searchTwitter("machine learning", n=500, lang="en")
mach_text = sapply(mach_tweets, function(x) x$getText())

# create a corpus
mach_corpus = Corpus(VectorSource(mach_text))

# create document term matrix applying some transformations
tdm = TermDocumentMatrix(mach_corpus, control = list(removePunctuation = TRUE,stopwords = c("machine", "learning", stopwords("english")), removeNumbers = TRUE, tolower = TRUE))

# define tdm as matrix
m = as.matrix(tdm)
# get word counts in decreasing order
word_freqs = sort(rowSums(m), decreasing=TRUE) 
# create a data frame with words and their frequencies
dm = data.frame(word=names(word_freqs), freq=word_freqs)

# plot wordcloud
wordcloud(dm$word, dm$freq, random.order=FALSE, colors=brewer.pal(8, "Dark2"))

# save the image in png format
png("MachineLearningCloud.png", width=12, height=8, units="in", res=300)
wordcloud(dm$word, dm$freq, random.order=FALSE, colors=brewer.pal(8, "Dark2"))
dev.off()