wordles.r

#N.B. On *ubuntu RCurl may not install for you off the bat. If so read: http://www.omegahat.org/RCurl/FAQ.html & sudo apt-get install libcurl4-openssl-dev 
install.packages(c("RCurl","twitteR","wordcloud","tm","stringr"))
library(twitteR); library(wordcloud); library(tm); library(stringr);

# Search for #mooc tweets
mooctweets <- searchTwitter("#mooc", n=2000)
length(mooctweets) # ends up with 713 as of 03-Jan-13 at 15:42 London time

# make into a data.frame
mooctweets_df <- twListToDF(mooctweets)
tail(mooctweets_df)

# Words used
cleaned <- sapply(mooctweets_df$text, function(x) str_trim(gsub("\"|@[A-Za-z.-_]+|(RT)|(MT)|[!:;]\\s+|http[s]?://[A-Za-z0-9]+\\.?[A-Za-z0-9]+/[A-Za-z0-9]+\\.?[A-Za-z0-9]+|#[A-Za-z0-9]+", "", x), "both"), USE.NAMES=F)
cleaned_coll <- paste(cleaned, collapse=" ") 
corpus <- Corpus(VectorSource(cleaned_coll))
moocCorpus <- tm_map(corpus, function(x)removeWords(x,stopwords()))

mooc_ <- TermDocumentMatrix(moocCorpus)
ap.m <- as.matrix(mooc_)
ap.v <- sort(rowSums(ap.m), decreasing=TRUE)
ap.d <- data.frame(word = names(ap.v),freq=ap.v)
table(ap.d$freq)
pal2 <- brewer.pal(8,"Dark2")
png("~/mooctweets.png", width=800, height=600)
wordcloud(ap.d$word,ap.d$freq, scale=c(8,.2),min.freq=2, max.words=100,
  				random.order=FALSE, rot.per=.15, colors=pal2)
dev.off()

# Users
userscorpus <- Corpus(VectorSource(mooctweets_df$screenName))
userscorpus_ <- tm_map(userscorpus, function(x)removeWords(x,stopwords()))

mooc_ <- TermDocumentMatrix(userscorpus_)
ap.m <- as.matrix(mooc_)
ap.v <- sort(rowSums(ap.m), decreasing=TRUE)
ap.d <- data.frame(word = names(ap.v),freq=ap.v)
table(ap.d$freq)
pal2 <- brewer.pal(8,"Dark2")
png("~/mooctweeters.png", width=800,height=600)
wordcloud(ap.d$word,ap.d$freq, scale=c(8,.2),min.freq=2, max.words=100,
					random.order=FALSE, rot.per=.15, colors=pal2)
dev.off()

If you get "Error in object[[i]] : object of type 'closure' is not subsettable"

then there's too many tweets.

1500 is the maximum if you're not specially authenticated by Twitter
http://stackoverflow.com/questions/10328066/twitter-package-in-r-maximum-tweets-using-searchtwitter