Twitter上的文本挖掘

Question

I am trying to follow tutorial 1 to do text mining on twitter My codes are:

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

mh370 <- searchTwitter("#PrayForMH370", since = "2014-03-08", until =     "2014-03-20", n = 1000)
mh370_text = sapply(mh370, function(x) x$getText())
mh370_corpus = Corpus(VectorSource(mh370_text))

tdm = TermDocumentMatrix(mh370_corpus,control = list(removePunctuation =     TRUE,stopwords = c("prayformh370", "prayformh",    stopwords("english")),removeNumbers = TRUE, tolower = TRUE))
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)
wordcloud(dm$word,dm$freq,random.order=FALSE,colors=brewer.pal(8,"Dark2"))

When I run the last code, I get this error:

Error in strwidth(words[i], cex = size[i], ...) : invalid 'cex' value
In addition: Warning messages:
1: In max(freq) : no non-missing arguments to max; returning -Inf
2: In max(freq) : no non-missing arguments to max; returning -Inf

Please advice.

Answer 1

As Vikram said, maybe you should reduce the number of words in your plot by adding max.words to your wordcloud.

wordcloud(dm$word, dm$freq, scale=c(8,3), min.freq=2, max.words=120,
          random.order=FALSE, colors=brewer.pal(8,"Dark2"))

I also suggest using min.freq to plot words that appear at least twice and scale to control the size of the words. Adjust those until you get a nice plot.

Answer 2

You may want to removeSparseTerms as well. I encountered a similar problem, and I found this solution some time ago. I had to modify the solution though, but removing sparse terms worked. tm package has the function.