Switch branches/tags
Nothing to show
Find file Copy path
08a2697 Jul 13, 2011
0 contributors

Users who have contributed to this file

52 lines (43 sloc) 1.92 KB
#' score.sentiment() implements a very simple algorithm to estimate
#' sentiment, assigning a integer score by subtracting the number
#' of occurrences of negative words from that of positive words.
#' @param sentences vector of text to score
#' @param pos.words vector of words of postive sentiment
#' @param neg.words vector of words of negative sentiment
#' @param .progress passed to <code>laply()</code> to control of progress bar.
#' @returnType data.frame
#' @return data.frame of text and corresponding sentiment scores
#' @author Jefrey Breen <>
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)