sentiment.R

# assuming you have downloaded the data (Data1.csv) correctly,
# as discussed here: https://piazza.com/class/l7oq25mqbrz1nd/post/110


# you may need to change the file location in quotes below, to suit where your file is
apple <- read.csv("~/Documents/Data1.csv", stringsAsFactors = F,  encoding="UTF-8")

str(apple)

library(tm)
corpus <- iconv(apple$text, "ASCII", "UTF-8")
corpus <- Corpus(VectorSource(corpus))
inspect(corpus[1:15])

corpus <- tm_map(corpus, tolower)
inspect(corpus[1:15])

corpus <- tm_map(corpus, removePunctuation)
inspect(corpus[1:15])

corpus <- tm_map(corpus, removeNumbers)
inspect(corpus[1:15])

cleanset <- tm_map(corpus, removeWords, stopwords('english'))
inspect(cleanset[1:15])

removeURL <- function(x) gsub('http[[:alnum:]]*', '', x)
cleanset <- tm_map(cleanset, content_transformer(removeURL))
inspect(cleanset[1:15])

cleanset <- tm_map(cleanset, removeWords, c('aapl', 'apple'))
cleanset <- tm_map(cleanset, gsub,
                   pattern = 'stocks',
                   replacement = 'stock')
cleanset <- tm_map(cleanset, stemDocument)
cleanset <- tm_map(cleanset, stripWhitespace)
inspect(cleanset[1:7])

tdm <- TermDocumentMatrix(cleanset)
tdm <- as.matrix(tdm)
tdm[1:10, 1:20]

w <- rowSums(tdm)
w <- subset(w, w>=25)
barplot(w,
        las = 2,
        col = rainbow(50))


library(wordcloud)
w <- sort(rowSums(tdm), decreasing = TRUE)
set.seed(222)
wordcloud(words = names(w),
          freq = w,
          max.words = 150,
          random.order = F,
          min.freq = 5,
          colors = brewer.pal(8, 'Dark2'),
          scale = c(5, 0.3),
          rot.per = 0.7)

install.packages("syuzhet")
library(syuzhet)

# you may need to change the file location in quotes below, to suit where your file is
apple <- read.csv("~/Documents/Data1.csv", stringsAsFactors = F,  encoding="UTF-8")
texts <- iconv(apple$text, "ASCII", "UTF-8", sub="byte")
raw_data$textCol<- iconv(raw_data$textCol, "ASCII", "UTF-8", sub="byte")


s <- get_nrc_sentiment(texts)
head(s)

barplot(colSums(s),
        las = 2,
        col = rainbow(10),
        ylab = 'Count',
        main = 'Sentiment Scores Tweets')