R Notebook

library(dplyr)

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

library(ggplot2)
library(wordcloud)

## Warning: package 'wordcloud' was built under R version 3.6.2

## Loading required package: RColorBrewer

library(SentimentAnalysis)

## Warning: package 'SentimentAnalysis' was built under R version 3.6.2

## 
## Attaching package: 'SentimentAnalysis'

## The following object is masked from 'package:base':
## 
##     write

library(ggplot2)
library(tm)

## Warning: package 'tm' was built under R version 3.6.2

## Loading required package: NLP

## 
## Attaching package: 'NLP'

## The following object is masked from 'package:ggplot2':
## 
##     annotate

#Load Data (2 columns, airline and tweet text)
tweets = read.csv("E:/TA Work Docs/Twitter Analysis/Tweets.csv")[ ,c('airline', 'text')]

str(tweets)

## 'data.frame':    500 obs. of  2 variables:
##  $ airline: Factor w/ 3 levels "Delta","Southwest",..: 2 2 2 2 2 2 2 1 1 1 ...
##  $ text   : Factor w/ 500 levels ". @SouthwestAir condescension must be a quality your co rewards. Your tone reeks of it",..: 410 261 379 333 340 320 366 483 484 80 ...

View(tweets)
#convert the Factor to character using as.character 
documents= as.character(tweets[,c("text")])
#Analyze sentiments
sentiment <- analyzeSentiment(documents)
tweetSentiments <- convertToDirection(sentiment$SentimentQDAP)
#Simple stacked bar chart of positive and negative sentiments by airline
ggplot(tweets, aes(tweets$airline, fill=tweetSentiments)) + geom_bar()

#Word cloud of positive tweets and negative tweets for each airline (wordcloud package)

docs <- Corpus(VectorSource(tweets$text))
docs <- tm_map(docs, content_transformer(tolower))

## Warning in tm_map.SimpleCorpus(docs, content_transformer(tolower)):
## transformation drops documents

docs <- tm_map(docs, removeNumbers)

## Warning in tm_map.SimpleCorpus(docs, removeNumbers): transformation drops
## documents

docs <- tm_map(docs, removeWords, stopwords("english"))

## Warning in tm_map.SimpleCorpus(docs, removeWords, stopwords("english")):
## transformation drops documents

docs <- tm_map(docs, removeWords, c("virginamerica" , "delta" , "southwest" ,"jetblue" ,"flights","southwestair")) 

## Warning in tm_map.SimpleCorpus(docs, removeWords, c("virginamerica",
## "delta", : transformation drops documents

docs <- tm_map(docs, removePunctuation)

## Warning in tm_map.SimpleCorpus(docs, removePunctuation): transformation
## drops documents

docs <- tm_map(docs, stripWhitespace)

## Warning in tm_map.SimpleCorpus(docs, stripWhitespace): transformation drops
## documents

dtm <- TermDocumentMatrix(docs)
m <- as.matrix(dtm)
v <- sort(rowSums(m),decreasing=TRUE)
d <- data.frame(word = names(v),freq=v)
head(d, 10)

wordcloud(words = d$word, freq = d$freq, min.freq = 1,
          max.words=200, random.order=FALSE, rot.per=0.35, 
          colors=brewer.pal(8, "Dark2"))