Sentiment Analysis

library(twitteR)
library(tm)

## Loading required package: NLP

library(ggplot2) 

## 
## Attaching package: 'ggplot2'

## The following object is masked from 'package:NLP':
## 
##     annotate

library(stringr)
library(RColorBrewer)
library(syuzhet)

library(twitteR)
#set Credentials
CONSUMER_SECRET <- "G39QeG1hxTn5lcxbVw5JOXGk0JD8diMIm1JWfkeKDCYV8MCvdo"
CONSUMER_KEY <- "25ZBYYAm2VIWomrnKgEFrfizf"
ACCESS_SECRET <- "7L6RSbD5QltdQIJbH6HYCrkM8du0QuqOhAs3DxNDv9kDD"
ACCESS_TOKEN <- "1391946408710664193-WCBR3AB4FwYBAVPggINbSDOeTKOTLm"
#connect to twitter app
setup_twitter_oauth(consumer_key = CONSUMER_KEY,
                    consumer_secret = CONSUMER_SECRET,
                    access_token = ACCESS_TOKEN,
                    access_secret = ACCESS_SECRET)

## [1] "Using direct authentication"

#GET TWITTER USER
twitterUser <- getUser("weareoneEXO")

tweets <- searchTwitter("weareoneEXO", n = 5000, 
                        since = "2021-05-03", 
                        until ="2021-05-09", 
                        lang ="en",
                        retryOnRateLimit = 120)

#convert tweets to tweets.df
tweets.df = twListToDF(tweets)

#extract timeline tweets 
extractTimelineTweets <- function(username,tweetCount){ 
  # timeline tweets 
  twitterUser <- getUser(username) 
  tweets = userTimeline(twitterUser,n=tweetCount) 
  tweets.df = twListToDF(tweets) 
  issue.df$text <- sapply(tweets.df$text,function(x) iconv(enc2utf8(x), sub="byte")) 
  
  return(tweeets.df) 
}   
encodeSentiment <- function(x) { 
  if(x <= -0.5){ 
    "1) very negative" 
  }else if(x > -0.5 & x < 0){ 
    "2) negative" 
  }else if(x > 0 & x < 0.5){ 
    "4) positive" 
  }else if(x >= 0.5){ 
    "5) very positive" 
  }else { 
    "3) neutral" 
  } 
}  

#sentiment analysis 
tweetSentiments <- get_sentiment (tweets.df$text,method = "syuzhet") 
tweets <- cbind(tweets.df, tweetSentiments) 

tweets$sentiment <- sapply(tweets$tweetSentiments,encodeSentiment) 
head(tweets, n = 1)  

##                                                                                                                             text
## 1 RT @EXOBBS50_CHARTS: Reply with your choice + #EXO #엑소 + @weareoneEXO \n\n🎯300 replies in 50 minutes https://t.co/7vTKKwBpoP
##   favorited favoriteCount replyToSN             created truncated replyToSID
## 1     FALSE             0      <NA> 2021-05-08 23:59:58     FALSE       <NA>
##                    id replyToUID
## 1 1391181109707292674       <NA>
##                                                                           statusSource
## 1 <a href="http://twitter.com/download/android" rel="nofollow">Twitter for Android</a>
##    screenName retweetCount isRetweet retweeted longitude latitude
## 1 effy_says17           74      TRUE     FALSE        NA       NA
##   tweetSentiments   sentiment
## 1             0.4 4) positive

qplot(tweets$tweetSentiments) + theme(legend.position="none")+ 
  xlab("Sentiment Score") + 
  ylab("Number of tweets") +  
  ggtitle("Tweets by Sentiment Score") 

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

# NRC Sample (various emotions such as anger, fear, joy, ...) 
tweetSentiments <- get_nrc_sentiment(tweets.df$text) 
head(tweetSentiments) 

##   anger anticipation disgust fear joy sadness surprise trust negative positive
## 1     0            0       0    0   0       0        0     0        0        1
## 2     0            0       0    0   0       0        0     0        0        0
## 3     0            0       0    0   0       0        0     0        0        0
## 4     0            0       0    0   0       0        0     0        0        0
## 5     0            1       0    0   0       0        0     1        0        1
## 6     0            0       0    0   0       0        0     0        0        0

tweets <- cbind(tweets.df, tweetSentiments) 
tweets[c(1:5),c(1, 17:26)]  

##                                                                                                                                             text
## 1                 RT @EXOBBS50_CHARTS: Reply with your choice + #EXO #엑소 + @weareoneEXO \n\n🎯300 replies in 50 minutes https://t.co/7vTKKwBpoP
## 2 RT @SMTownEngSub: It's been exactly 2 years since Xiumin's 2nd STATION single "You" was released\n\n@weareoneEXO #Xiumin https://t.co/0UgzJTw…
## 3                                        @mouna_exol WE NOMINATE #XIUMIN OF #EXO \n FOR #TBworld2021 #100MostHandsomeMen2021  @weareoneEXO \n.69
## 4 RT @SMTownEngSub: It's been exactly 2 years since Xiumin's 2nd STATION single "You" was released\n\n@weareoneEXO #Xiumin https://t.co/0UgzJTw…
## 5                         RT @exobrand50: #CHEN , #KYUNGSOO ,#SUHO & #XIUMIN are all trending in Twitter Top Trends🎉🎉🎉🎉\n\n@weareoneEXO #EXO
##   anger anticipation disgust fear joy sadness surprise trust negative positive
## 1     0            0       0    0   0       0        0     0        0        1
## 2     0            0       0    0   0       0        0     0        0        0
## 3     0            0       0    0   0       0        0     0        0        0
## 4     0            0       0    0   0       0        0     0        0        0
## 5     0            1       0    0   0       0        0     1        0        1

sentimentTotals <- data.frame(colSums(tweets[,c(17:26)]))  
names(sentimentTotals) <- "count" 

sentimentTotals <- cbind("sentiment" = rownames(sentimentTotals), sentimentTotals) 
rownames(sentimentTotals) <- NULL 
sentimentTotals  

##       sentiment count
## 1         anger   370
## 2  anticipation  1065
## 3       disgust   101
## 4          fear   366
## 5           joy  1012
## 6       sadness   404
## 7      surprise   645
## 8         trust  1377
## 9      negative   537
## 10     positive  1998

ggplot(data = sentimentTotals, aes(x = sentiment, y = count)) + 
  geom_bar(aes(fill = sentiment), stat = "identity") + 
  theme(legend.position = "none") + 
  xlab("Sentiment") + ylab("Total Count") + ggtitle("Total Sentiment Score for All Tweets")