Created
March 13, 2016 08:25
-
-
Save hanxue/0c9c266b63efbb28896a to your computer and use it in GitHub Desktop.
Twitter WordCloud for Najib Using R
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
library(twitteR) | |
library(ROAuth) | |
library(tm) | |
library(plyr) | |
library(ggplot2) | |
library(wordcloud) | |
library(RColorBrewer) | |
library(XML) | |
my.key <- Sys.getenv("TWITTER_KEY") | |
my.secret <- Sys.getenv("TWITTER_SECRET") | |
access.token <- Sys.getenv("TWITTER_TOKEN") | |
access.token.secret <- Sys.getenv("TWITTER_TOKEN_SECRET") | |
setup_twitter_oauth(my.key, my.secret, access.token, access.token.secret) | |
register_sqlite_backend("/usr/local/var/sqlite/sentiment_najib") | |
table_name <- "najib" | |
latest_tweet <- get_latest_tweet_id(table_name = table_name) | |
tweets <- searchTwitteR("Najib", n = 3000, sinceID = latest_tweet) | |
store_tweets_db(tweets, table_name = table_name) | |
# Uncomment next line to process all tweets in database | |
# tweets <- load_tweets_db(table_name = table_name) | |
# Prepare malay stopwords | |
df1 <- readHTMLTable('http://blog.kerul.net/2014/01/list-of-malay-stop-words.html') | |
df1 <- df1[[1]] | |
malaystopwords <- as.character(unlist(df1))[-c(320, 321)] | |
malaystopwords <- c(malaystopwords, "najib", "razak", "...") | |
remove_url <- function(x) { | |
gsub("\\bhttp(s?)://(.*)+|@(.*)+|[,.:]$", "", x) | |
} | |
corpus = Corpus(VectorSource(sapply(tweets, function(x) x$getText()))) | |
corpus <- tm_map(corpus, function(x) iconv(x, to='UTF-8', sub='')) | |
corpus = tm_map(corpus, tolower) | |
corpus = tm_map(corpus, remove_url) | |
corpus = tm_map(corpus, function(x) removeWords(x, stopwords("english"))) | |
corpus = tm_map(corpus, function(x) removeWords(x, malaystopwords)) | |
corpus = tm_map(corpus, removeNumbers) | |
corpus = tm_map(corpus, removePunctuation) | |
corpus = tm_map(corpus, PlainTextDocument) | |
col = brewer.pal(6, "Dark2") | |
wordcloud(corpus, min.freq = 25, scale = c(3, 0.3), rot.per = 0.25, | |
random.color = T, max.words = 100, random.order = FALSE, | |
colors = col) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment