3. TwitterR [ R : 영어 with 감정스코어 ]

negative-words.txt

positive-words.txt

apple <- searchTwitter("@apple",n=1000)

length(apple)

class(apple)

head(apple)

tweet.apple <- apple[[1]]

tweet.apple$getId()

tweet.apple$favoriteCount

tweet.apple$getScreenName()  # ID확인

tweet.apple$text #내용.

apple.text <- laply(apple, function(t) t$getText())

head(apple.text)

pos.word <- scan("positive-words.txt",what="character",comment.char = ";")

neg.word <- scan("negative-words.txt",what="character",comment.char = ";")

pos.word <- c(pos.word,"upgrade")

neg.word <- c(neg.word,"wait","waiting")

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

{

  require(plyr)

  require(stringr)

  # we got a vector of sentences. plyr will handle a list or a vector as an "l" for us

  # we want a simple array ("a") 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 = !is.na(pos.matches)

    neg.matches = !is.na(neg.matches)

    # and conveniently enough, TRUE/FALSE will be treated as 1/0 by sum():

    score = sum(pos.matches) - sum(neg.matches)

    return(score)

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

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

  return(scores.df)

}

apple.text <- apple.text[!Encoding(apple.text)=="UTF-8"]

apple.score <- score.sentiment(apple.text,pos.word,neg.word,.progress = 'text')

hist(apple.score$score)