Function to do sentiment analysis (on twitter data for example)

# based on

score.sentiment = function(sentences, pos.words, neg.words, .progress=’none’)

# we got a vector of sentences. plyr will handle a list or a vector as an “l” for us
# we want a simple array of scores back, so we use “l” + “a” + “ply” = laply:
scores = laply(sentences, function(sentence, pos.words, neg.words) {

# clean up sentences with R’s regex-driven global substitute, gsub():
sentence = gsub(‘[[:punct:]]’, ”, sentence)
sentence = gsub(‘[[:cntrl:]]’, ”, sentence)
sentence = gsub(‘\\d+’, ”, sentence)
# and convert to lower case:
sentence = tolower(sentence)

# split into words. str_split is in the stringr package
word.list = str_split(sentence, ‘\\s+’)
# sometimes a list() is one level of hierarchy too much
words = unlist(word.list)

# compare our words to the dictionaries of positive & negative terms
pos.matches = match(words, pos.words)
neg.matches = match(words, neg.words)

# match() returns the position of the matched term or NA
# we just want a TRUE/FALSE:
pos.matches = !
neg.matches = !

# and conveniently enough, TRUE/FALSE will be treated as 1/0 by sum():
score = sum(pos.matches) – sum(neg.matches)

}, pos.words, neg.words, .progress=.progress )

scores.df = data.frame(score=scores, text=sentences)


Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s