#Load installed packages
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)
CONSUMER_SECRET <-"LtZOaw4W6wbaB6grqlmcaeZzBUX0GRLih3YGHskZoRHzvWSxdh"
CONSUMER_KEY <- "wuZ6OITxlU99FjjE2USFa4Zf8"
ACCESS_SECRET <- "09qXsDWA3AiFELPO2OXJGpCvsrdEiCgfxL47MijugXmu5"
ACCESS_TOKEN <- "1390086794901737474-H5hAlP06rhqyolbSQV1lhUEA0hZMXR"
setup_twitter_oauth(consumer_key = CONSUMER_KEY,
consumer_secret = CONSUMER_SECRET,
access_token = ACCESS_TOKEN,
access_secret = ACCESS_SECRET)
## [1] "Using direct authentication"
twitterUser <- getUser("vicegandako")
tweets <- searchTwitter("vicegandako", n = 5000,
since = "2021-05-01",
until ="2021-05-07",
lang ="en",
retryOnRateLimit = 120)
## Warning in doRppAPICall("search/tweets", n, params = params, retryOnRateLimit =
## retryOnRateLimit, : 5000 tweets were requested but the API can only return 669
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$text,method = "syuzhet")
tweets <- cbind(tweets.df, tweetSentiments)
#positive and negative sentiments
tweets$sentiment <- sapply(tweets$tweetSentiments,encodeSentiment)
head(tweets, n = 1)
## text
## 1 RT @CHIMANDATrends: We trended today! Thank you for joining us, Team CM, Team A & Team C! Hopefully, maging guest rin sa It's Showtime Tago…
## favorited favoriteCount replyToSN created truncated replyToSID
## 1 FALSE 0 <NA> 2021-05-06 23:59:58 FALSE <NA>
## id replyToUID
## 1 1390456334865166341 <NA>
## statusSource
## 1 <a href="http://twitter.com/download/android" rel="nofollow">Twitter for Android</a>
## screenName retweetCount isRetweet retweeted longitude latitude
## 1 VelascoJoannah 13 TRUE FALSE NA NA
## tweetSentiments sentiment
## 1 1.1 5) very positive
qplot(tweets$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 1 0 0
## 2 0 0 0 0 0 0 0 2 0 3
## 3 0 0 0 0 0 0 0 2 0 3
## 4 0 0 0 0 0 0 0 0 0 0
## 5 0 0 0 0 0 0 0 0 0 0
## 6 1 1 0 0 0 0 1 1 0 0
tweets <- cbind(tweets.df, tweetSentiments)
tweets[c(1:5),c(1, 17:26)]
## text
## 1 RT @CHIMANDATrends: We trended today! Thank you for joining us, Team CM, Team A & Team C! Hopefully, maging guest rin sa It's Showtime Tago…
## 2 @vicegandako Hello hoomans! Looking for academic helper? Need to rest? Tinatamad? Check my service for a student-fr… https://t.co/LTg86sJlVN
## 3 @vicegandako Hello hoomans! Looking for academic helper? Need to rest? Tinatamad? Check my service for a student-fr… https://t.co/njV9u0RI6j
## 4 RT @AprilJi79102256: ILoveYou Both \U0001f970💋😍\n@vicegandako / Ion Perez\n\n#MrAndMrsPerez https://t.co/JH3ithyHe1
## 5 😂😂😂🤣🤣🤣 \n@vicegandako @VhongX44 @anakarylle @prinsesachinita @ryanbang @jugsjugsjugs @teddspotting @itsShowtimeNa… https://t.co/331wk0ZgOP
## anger anticipation disgust fear joy sadness surprise trust negative positive
## 1 0 0 0 0 0 0 0 1 0 0
## 2 0 0 0 0 0 0 0 2 0 3
## 3 0 0 0 0 0 0 0 2 0 3
## 4 0 0 0 0 0 0 0 0 0 0
## 5 0 0 0 0 0 0 0 0 0 0
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 77
## 2 anticipation 159
## 3 disgust 43
## 4 fear 74
## 5 joy 392
## 6 sadness 53
## 7 surprise 58
## 8 trust 233
## 9 negative 174
## 10 positive 483
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")
