http://stackoverflow.com/questions/15058485/oauth-with-twitter-streaming-api-in-r-using-rcurl
https://sites.google.com/site/miningtwitter/questions/talking-about/wordclouds/comparison-cloud
library(RCurl) library(twitteR) library(ROAuth) requestURL <- "https://api.twitter.com/oauth/request_token" accessURL = "http://api.twitter.com/oauth/access_token" authURL = "http://api.twitter.com/oauth/authorize" #consumerKey = "myconsumerkeystring" #consumerSecret = "myconsumersecretstring" consumerKey = "wwM3rXUWd48ImpjxljgA" consumerSecret= "X22dmkq7MjWxV5PoMDs8Qwkq7MOvJjHUMbdutIaw" Cred <- OAuthFactory$new(consumerKey=consumerKey, consumerSecret=consumerSecret, requestURL=requestURL, accessURL=accessURL, authURL=authURL) Cred$handshake(cainfo = system.file("CurlSSL", "cacert.pem", package = "RCurl") ) registerTwitterOAuth(Cred)
# att tweets att_tweets = userTimeline("moyahima", n=1000) # verizon tweets ver_tweets = userTimeline("ryooopan", n=1000) # verizon tweest mob_tweets = userTimeline("satomacoto", n=1000) # metro pcs tweets pcs_tweets = userTimeline("ken_nishi", n=1000) # get text att_txt = sapply(att_tweets, function(x) x$getText()) ver_txt = sapply(ver_tweets, function(x) x$getText()) mob_txt = sapply(mob_tweets, function(x) x$getText()) pcs_txt = sapply(pcs_tweets, function(x) x$getText()) clean.text = function(x) { # tolower x = tolower(x) # remove rt x = gsub("rt", "", x) # remove at x = gsub("@\\w+", "", x) # remove punctuation x = gsub("[[:punct:]]", "", x) # remove numbers x = gsub("[[:digit:]]", "", x) # remove links http x = gsub("http\\w+", "", x) # remove tabs x = gsub("[ |\t]{2,}", "", x) # remove blank spaces at the beginning x = gsub("^ ", "", x) # remove blank spaces at the end x = gsub(" $", "", x) return(x) } # clean texts att_clean = clean.text(att_txt) ver_clean = clean.text(ver_txt) mob_clean = clean.text(mob_txt) pcs_clean = clean.text(pcs_txt) att = paste(att_clean, collapse=" ") ver = paste(ver_clean, collapse=" ") mob = paste(mob_clean, collapse=" ") pcs = paste(pcs_clean, collapse=" ") # put everything in a single vector all = c(att, ver, mob, pcs) # remove stop-words all = removeWords(all, c(stopwords("english"), "att", "verizon", "tmobile", "metropcs")) # create corpus corpus = Corpus(VectorSource(all)) # create term-document matrix tdm = TermDocumentMatrix(corpus) # convert as matrix tdm = as.matrix(tdm) # add column names colnames(tdm) = c("moyahima", "ryooopan", "satomacoto", "ken_nishi") pdf("CarriersCompCloud.pdf", width=8, height=8) comparison.cloud(tdm, random.order=FALSE, colors = c("#00B2FF", "red", "#FF0099", "#6600CC"), title.size=1.5, max.words=500) dev.off() pdf("CarriersCommCloud.pdf", width=8, height=8) commonality.cloud(tdm, random.order=FALSE, colors = brewer.pal(8, "Dark2"), title.size=1.5) dev.off()
比較
共通
