Simple way to build twitter word cloud

main.R

twitter.results <- searchTwitter('#stylight', cainfo="cacert.pem")
df <- do.call("rbind", lapply(twitter.results, as.data.frame))

# rename metadata
names.twitteR <- c("screenName", "created") # change from
names.api <- c("screen_name", "created_at") # change to
for(name in names.twitteR) {
    names(df)[which(names(df)==name)] <- names.api[which(names.twitteR==name)]
}
df$from_user <- df$screen_name

And our base task to execute

# load source file first
source("semantic_analysis.R")

# construct corpus, with regular preprocessing performed
corpus <- ConstructCorpus(df$text, removeTags = TRUE, removeUsers = TRUE)

# make a word cloud
MakeWordCloud(corpus)

OAuthFactory.R

reqURL <- "https://api.twitter.com/oauth/request_token"
accessURL <- "http://api.twitter.com/oauth/access_token"
authURL <- "http://api.twitter.com/oauth/authorize"
consumerKey <- 'consumerKey'
consumerSecret <- 'consumerSecret'
twitCred <- OAuthFactory$new(consumerKey=consumerKey,
                             consumerSecret=consumerSecret,
                             requestURL=reqURL,
                             accessURL=accessURL,
                             authURL=authURL)

twitCred$handshake()

semantic_analysis.R

ConstructCorpus <- function(textVec, 
                            toLower = TRUE, 
                            removePunctuations = TRUE, 
                            removeStopwords = TRUE, 
                            removeNumbers = FALSE, 
                            stemming = FALSE,
                            removeTags = FALSE, 
                            removeUsers = FALSE) {
  # Construct text corpus
  
  more.stopwords <- c("via", "rt", "mt", "amp")
  
  EnsurePackage("tm")
  
  # create a object
  corpus <- Corpus(VectorSource(textVec))
  
  if(toLower) corpus <- tm_map(corpus, tolower)
  
  if(removeTags) {
    source("utilities.R")
    corpus <- tm_map(corpus, TrimHashtags)
  }
  if(removeUsers) {
    source("utilities.R")
    corpus <- tm_map(corpus, TrimUsers)
  }
  
  if(removePunctuations) corpus <- tm_map(corpus, removePunctuation) 
  if(removeNumbers) corpus <- tm_map(corpus, removeNumbers)
  if(removeStopwords) corpus <- tm_map(corpus, function(x) 
    removeWords(x, append(stopwords("english"), more.stopwords)))
  
  if(stemming) {
    EnsurePackage("rJava")
    EnsurePackage("Snowball")
    corpus <- tm_map(corpus, stemDocument, language = "english")
  }
  
  
  
  return(corpus)
}

MakeWordCloud <- function(corpus) {
  # Make a word cloud
  #
  # Args:
  #   textVec: a text vector
  #
  # Returns:
  #   A word cloud created from the text vector
  
  EnsurePackage("tm")
  EnsurePackage("wordcloud")
  EnsurePackage("RColorBrewer")
  
  corpus <- tm_map(corpus, function(x) {
    removeWords(x, c("via", "rt", "mt"))
  })
  
  ap.tdm <- TermDocumentMatrix(corpus)
  ap.m <- as.matrix(ap.tdm)
  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")
  
  wordcloud(ap.d$word, ap.d$freq, 
            scale=c(8, .2), min.freq = 3, 
            max.words = Inf, random.order = FALSE, 
            rot.per = .15, colors = pal2)
}