Twitter Sentiment Analysis for CVS Health
This is a Notebook for Twitter Sentiment Analysis on CVS Health and CVS Aetna merger.
# Load Requried Packages
library("SnowballC")
library("tm")
library("twitteR")
library("syuzhet")
library("wordcloud")Setting up Twitter OAuth
consumer_key <- 'elVqMFVWgCUQBEDOR7vsfFsI7'
consumer_secret <- '5LizGPvZIZoHYojLhYFrfFXm2KjjIeCPvFwNiIhcOfdnAGzrKO'
access_token <- '380945634-TLTP7C0llQjRu4S5jPJvHKadGJnQ0V8m9DPrAhur'
access_secret <- 'XX26mpkPytRrlKi38tQDdE36RgE9s04KA8Q2FEsPYg14B'
setup_twitter_oauth(consumer_key,consumer_secret,access_token,access_secret)## [1] "Using direct authentication"tweets <- userTimeline("CVSHealth", n=200)
n.tweet <- length(tweets)#save text
tweets_text <- sapply(tweets, function(x) x$getText())
#create corpus - Constructs a text document collection (corpus).
tweets_text_corpus <- Corpus(VectorSource(tweets_text))tweets_text_corpus <- tm_map(tweets_text_corpus, function(x) iconv(enc2utf8(x), sub = "byte"))## Warning in tm_map.SimpleCorpus(tweets_text_corpus, function(x)
## iconv(enc2utf8(x), : transformation drops documentstweets_text_corpus <- tm_map(tweets_text_corpus, content_transformer(tolower)) ## Warning in tm_map.SimpleCorpus(tweets_text_corpus,
## content_transformer(tolower)): transformation drops documentstweets_text_corpus <- tm_map(tweets_text_corpus, removePunctuation)## Warning in tm_map.SimpleCorpus(tweets_text_corpus, removePunctuation):
## transformation drops documentstweets_text_corpus <- tm_map(tweets_text_corpus, function(x)removeWords(x,stopwords()))## Warning in tm_map.SimpleCorpus(tweets_text_corpus, function(x)
## removeWords(x, : transformation drops documentswordcloud(as.character(tweets_text_corpus))## Warning in tm_map.SimpleCorpus(corpus, removePunctuation): transformation
## drops documents## Warning in tm_map.SimpleCorpus(corpus, function(x) removeWords(x,
## stopwords())): transformation drops documents## Warning in wordcloud(as.character(tweets_text_corpus)): cvshealth could not
## be fit on page. It will not be plotted.
tweets.df <- twListToDF(tweets)
# head(tweets.df)
#
# head(tweets.df$text)We checked the Twitter Sentiments to see how that is affecting the deal : http://rpubs.com/SShivakumar/TwitterSentimentAnalysis
tweets.df2 <- gsub("http.*","",tweets.df$text)
tweets.df2 <- gsub("https.*","",tweets.df2)
tweets.df2 <- gsub("#.*","",tweets.df2)
tweets.df2 <- gsub("@.*","",tweets.df2)word.df <- as.vector(tweets.df2)
emotion.df <- get_nrc_sentiment(word.df)
emotion.df2 <- cbind(tweets.df2, emotion.df)
head(emotion.df2)## tweets.df2
## 1
## 2 .
## 3 .
## 4 .
## 5 Our pharmacists see every day how the opioid epidemic impacts communities. We recognize how critical it is to utili
## 6 Learn more about
## anger anticipation disgust fear joy sadness surprise trust negative
## 1 0 0 0 0 0 0 0 0 0
## 2 0 0 0 0 0 0 0 0 0
## 3 0 0 0 0 0 0 0 0 0
## 4 0 0 0 0 0 0 0 0 0
## 5 1 1 1 1 0 1 1 0 1
## 6 0 0 0 0 0 0 0 0 0
## positive
## 1 0
## 2 0
## 3 0
## 4 0
## 5 0
## 6 1sent.value <- get_sentiment(word.df)
most.positive <- word.df[sent.value == max(sent.value)]
most.positive## [1] "Learn how Coram CVS Specialty Infusion Services (Coram) & our high-touch model helps provide one-on-one support for
"most.negative <- word.df[sent.value <= min(sent.value)]
most.negative ## [1] "Our pharmacists see every day how the opioid epidemic impacts communities. We recognize how critical it is to utili
"sent.value## [1] 0.00 0.00 0.00 0.00 -1.35 0.80 0.40 2.30 0.00 0.00 0.00
## [12] -0.60 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 1.80
## [23] 0.75 0.00 0.00 0.00 -0.85 0.00 0.00 0.00 0.25 0.00 -0.50
## [34] 0.00 0.00 1.40 0.00 0.00 3.30 0.00 0.00 0.00 0.50 0.50
## [45] 0.00 0.50 0.50 -0.85 1.50 0.00 1.00 0.00 0.00 1.80 0.00
## [56] 0.50 1.80 0.00 0.00 0.00 0.30 0.00 0.00 0.00 1.00 1.10
## [67] 0.50 0.00 3.30 0.00 1.10 0.00 0.40 0.00 0.80 0.00 0.00
## [78] 0.00 0.00 0.00 0.00 0.00 0.80 0.00 0.00 0.00 3.25 0.80
## [89] 0.00 2.00 0.00 0.00 0.00 0.90 0.00 0.00 0.00 0.00 0.00
## [100] 0.00 0.00 2.10 0.00 0.00 1.15 0.00 0.00 1.00 0.00 0.00
## [111] 0.45 0.00 0.00 0.00 1.05 0.00 0.00 0.00 0.00 0.00 1.30
## [122] 2.25 0.00 0.15 0.00 0.00 0.80 0.00 0.50 0.00 1.80 0.00
## [133] 0.00 -0.85 0.80 3.25 0.00 0.00 0.00 1.00 1.55 0.00 1.25
## [144] 0.00 0.00 1.55 0.40 0.00 0.00 0.00 0.00 0.00 0.40 0.00
## [155] -0.20 0.00 0.00 0.00 1.55 0.75 0.00 0.00 2.50 0.00 0.75
## [166] 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
## [177] 0.80 0.60 0.00 0.00 0.00 0.00 0.40positive.tweets <- word.df[sent.value > 0]
head(positive.tweets)## [1] "Learn more about "
## [2] "32 new medication disposal units will be installed in "
## [3] "Providing Real-Time Benefits to Bring Savings to Patients "
## [4] "Health Care Consumerism: Making Health Care More Convenient "
## [5] "Today is the 1st day of summer! When traveling with kids this season, be sure to keep them safe by putting medicine
"
## [6] "News | CVS Health CEO Larry Merlo to Discuss Disruption and Transformation in Health Care During the 2018 Aspen Ide
"negative.tweets <- word.df[sent.value < 0]
head(negative.tweets)## [1] "Our pharmacists see every day how the opioid epidemic impacts communities. We recognize how critical it is to utili
"
## [2] "Have you disposed of unused prescription drugs at a local collection site?"
## [3] "News | CVS Health Expands Safe Drug Disposal at CVS Pharmacy Locations in Arizona to Help Combat Opioid Abuse "
## [4] "Kevin Hourican, Executive Vice President, CVS Health & President, CVS Pharmacy for "
## [5] "News | CVS Health Expands Safe Drug Disposal at CVS Pharmacy Locations in Virginia to Help Combat Opioid Abuse "
## [6] "Safely disposing of unwanted or unused medication is one element of our company-wide approach to address the
"neutral.tweets <- word.df[sent.value == 0]
head(neutral.tweets)## [1] "" "." "." "." "." ""category_senti <- ifelse(sent.value < 0, "Negative", ifelse(sent.value > 0, "Positive", "Neutral"))
head(category_senti)## [1] "Neutral" "Neutral" "Neutral" "Neutral" "Negative" "Positive"head(category_senti)## [1] "Neutral" "Neutral" "Neutral" "Neutral" "Negative" "Positive"category_senti2 <- cbind(tweets,category_senti)
head(category_senti2) #tweets category_senti senti## tweets category_senti
## [1,] ? "Neutral"
## [2,] ? "Neutral"
## [3,] ? "Neutral"
## [4,] ? "Neutral"
## [5,] ? "Negative"
## [6,] ? "Positive"sentiment_categories <- table(category_senti)
sentiment_categories## category_senti
## Negative Neutral Positive
## 7 120 56There is more percentage of positive sentiments in the tweets on both CVSHealth and CVSAetna.
plot(table(category_senti), main="Twitter Sentiments")
pie(sentiment_categories, main="Twitter Sentiments", labels=c("Negative","Neutral","Positive"), cex=0.8)