Sentiment Analysis R Notebook

R Markdown

This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.

When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:

Install required packages

#install the necessary packages
# install.packages("readr")
# install.packages("plyr")
# install.packages("stringr")
# install.packages("stringi")
# install.packages("magrittr")
# install.packages("dplyr")
# install.packages('tm')
# install.packages('RColorBrewer')
# install.packages('wordcloud')

Clean data

library(readr)
gear <- read.csv("Samsung Tweets.csv", row.names=1, sep=";")
geartweets <- gear$tweettext

#********************************************
#         Clean tweets
#********************************************
#use this function to clean the tweets
clean.text = function(x)
{
  # tolower
  x = tolower(x)
  # remove rt
  x = gsub("rt", "", x)
  # remove at
  x = gsub("@\\w+", "", x)
  # remove punctuation
  x = gsub("[[:punct:]]", "", x)
  # remove numbers
  x = gsub("[[:digit:]]", "", x)
  # remove links http
  x = gsub("http\\w+", "", x)
  # remove tabs
  x = gsub("[ |\t]{2,}", "", x)
  # remove blank spaces at the beginning
  x = gsub("^ ", "", x)
  # remove blank spaces at the end
  x = gsub(" $", "", x)
  return(x)
}

# clean tweets
geartweets = clean.text(geartweets)

Topic Analysis

sports.words = scan('Sports_Word.txt', what='character', comment.char=';')

score.topic = function(sentences, dict, .progress='none')
{
  require(plyr)
  require(stringr)
  require(stringi)
  
  # we got a vector of sentences. plyr will handle a list
  # or a vector as an "l" for us
  # we want a simple array of scores back, so we use
  # "l" + "a" + "ply" = "laply":
  scores = laply(sentences, function(sentence, dict) {
    
    # clean up sentences with R's regex-driven global substitute, gsub():
    sentence = gsub('[[:punct:]]', '', sentence)
    sentence = gsub('[[:cntrl:]]', '', sentence)
    sentence = gsub('\\d+', '', sentence)
    # and convert to lower case:
    sentence = tolower(sentence)
    
    # split into words. str_split is in the stringr package
    word.list = str_split(sentence, '\\s+')
    # sometimes a list() is one level of hierarchy too much
    words = unlist(word.list)
    
    # compare our words to the dictionaries of positive & negative terms
    topic.matches = match(words, dict)
    
    # match() returns the position of the matched term or NA
    # we just want a TRUE/FALSE:
    topic.matches = !is.na(topic.matches)
    
    # and conveniently enough, TRUE/FALSE will be treated as 1/0 by sum():
    score = sum(topic.matches)
    
    return(score)
  }, dict, .progress=.progress )
  
  topicscores.df = data.frame(score=scores, text=sentences)
  return(topicscores.df)
}

topic.scores = score.topic(geartweets, sports.words, .progress='none')

## Loading required package: plyr

## Loading required package: stringr

## Loading required package: stringi

Sentiment Analysis of Sports

pos.words = scan('positive-words.txt', what='character', comment.char=';')
neg.words = scan('negative-words.txt', what='character', comment.char=';')

neg.words = c(neg.words, 'wtf', 'fail')

#Implementing our sentiment scoring algorithm
require(plyr)
require(stringr)
require(stringi)

score.sentiment = function(sentences, pos.words, neg.words, .progress='none')
{
  
  # we got a vector of sentences. plyr will handle a list
  # or a vector as an "l" for us
  # we want a simple array of scores back, so we use
  # "l" + "a" + "ply" = "laply":
  scores = laply(sentences, function(sentence, pos.words, neg.words) {
    
    # clean up sentences with R's regex-driven global substitute, gsub():
    sentence = gsub('[[:punct:]]', '', sentence)
    sentence = gsub('[[:cntrl:]]', '', sentence)
    sentence = gsub('\\d+', '', sentence)
    # and convert to lower case:
    sentence = tolower(sentence)
    
    # split into words. str_split is in the stringr package
    word.list = str_split(sentence, '\\s+')
    # sometimes a list() is one level of hierarchy too much
    words = unlist(word.list)
    
    # compare our words to the dictionaries of positive & negative terms
    pos.matches = match(words, pos.words)
    neg.matches = match(words, neg.words)
    
    # match() returns the position of the matched term or NA
    # we just want a TRUE/FALSE:
    pos.matches = !is.na(pos.matches)
    neg.matches = !is.na(neg.matches)
    
    # and conveniently enough, TRUE/FALSE will be treated as 1/0 by sum():
    score = sum(pos.matches) - sum(neg.matches)
    
    return(score)
  }, pos.words, neg.words, .progress=.progress )
  
  scores.df = data.frame(score=scores, text=sentences)
  return(scores.df)
}

sentiment.scores= score.sentiment(topic.scores$text, pos.words, neg.words, .progress='none')

score <- sentiment.scores$score

library(plotly)

## Loading required package: ggplot2

## 
## Attaching package: 'plotly'

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

## The following objects are masked from 'package:plyr':
## 
##     arrange, mutate, rename, summarise

## The following object is masked from 'package:stats':
## 
##     filter

## The following object is masked from 'package:graphics':
## 
##     layout

p <- plot_ly(x = ~score, type = "histogram")
p

Topic Analysis of Positive, Negative, and Neutral words

pos.words = scan('positive-words.txt', what='character', comment.char=';')
neg.words = scan('negative-words.txt', what='character', comment.char=';')

neg.words = c(neg.words, 'wtf', 'fail')

#Implementing our sentiment scoring algorithm
require(plyr)
require(stringr)
require(stringi)

score.sentiment = function(sentences, pos.words, neg.words, .progress='none')
{
  
  # we got a vector of sentences. plyr will handle a list
  # or a vector as an "l" for us
  # we want a simple array of scores back, so we use
  # "l" + "a" + "ply" = "laply":
  scores = laply(sentences, function(sentence, pos.words, neg.words) {
    
    # clean up sentences with R's regex-driven global substitute, gsub():
    sentence = gsub('[[:punct:]]', '', sentence)
    sentence = gsub('[[:cntrl:]]', '', sentence)
    sentence = gsub('\\d+', '', sentence)
    # and convert to lower case:
    sentence = tolower(sentence)
    
    # split into words. str_split is in the stringr package
    word.list = str_split(sentence, '\\s+')
    # sometimes a list() is one level of hierarchy too much
    words = unlist(word.list)
    
    # compare our words to the dictionaries of positive & negative terms
    pos.matches = match(words, pos.words)
    neg.matches = match(words, neg.words)
    
    # match() returns the position of the matched term or NA
    # we just want a TRUE/FALSE:
    pos.matches = !is.na(pos.matches)
    neg.matches = !is.na(neg.matches)
    
    # and conveniently enough, TRUE/FALSE will be treated as 1/0 by sum():
    score = sum(pos.matches) - sum(neg.matches)
    
    return(score)
  }, pos.words, neg.words, .progress=.progress )
  
  scores.df = data.frame(score=scores, text=sentences)
  return(scores.df)
}

sentiment.scores= score.sentiment(geartweets, pos.words, neg.words, .progress='none')
pos.mentioned = subset(sentiment.scores, score > 0)
neu.mentioned = subset(sentiment.scores, score == 0)
neg.mentioned = subset(sentiment.scores, score < 0)

N= nrow(sentiment.scores)
Npos = nrow(pos.mentioned)
Nneu = nrow(neu.mentioned)
Nneg = nrow(neg.mentioned)

dftemp=data.frame(topic=c("Positive", "Negative", "Neutral" ), 
                  number=c(Npos, Nneg, Nneu))


library(plotly)
p <- plot_ly(data=dftemp, labels = ~topic, values = ~number, type = 'pie') %>%
  layout(title = 'Pie Chart of Tweets mentioning Positive, Negative and Neutral',
         xaxis = list(showgrid = FALSE, zeroline = FALSE, showticklabels = FALSE),
         yaxis = list(showgrid = FALSE, zeroline = FALSE, showticklabels = FALSE))
p

Word cloud of negative tweets

require(tm)

## Loading required package: tm

## Loading required package: NLP

## 
## Attaching package: 'NLP'

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

require(wordcloud)

## Loading required package: wordcloud

## Loading required package: RColorBrewer

require(RColorBrewer)

negativeTweets = subset(sentiment.scores, score < 0)$text

corpus = Corpus(VectorSource(negativeTweets))
# corpus = Corpus(VectorSource(cmail))
# create term-document matrix
tdm = TermDocumentMatrix(
  corpus,
  control = list(
    wordLengths=c(3,20),
    removePunctuation = TRUE,
    stopwords = c("the", "a", stopwords("english")),
    removeNumbers = TRUE, tolower = TRUE) )

# convert as matrix
tdm = as.matrix(tdm)

# get word counts in decreasing order
word_freqs = sort(rowSums(tdm), decreasing=TRUE) 
word_freqs = word_freqs[-(1:12)]
# create a data frame with words and their frequencies
dm = data.frame(word=names(word_freqs), freq=word_freqs)

#Plot corpus in a clored graph; need RColorBrewer package

wordcloud(head(dm$word, 100), head(dm$freq, 100), random.order=FALSE, colors=brewer.pal(8, "Dark2"))

#check top 50 most mentioned words
head(word_freqs, 50)

##          sma     mercedes       review         time       iphone 
##          241          215          202          198          175 
##          new        still         gear          amp   technology 
##          170          166          152          138          135 
##          bad         afar         just          que         good 
##          128          116          103           99           99 
##         ugly        wrist          die          one          del 
##           98           97           95           93           86 
##         date   integrated          sin      release       launch 
##           85           84           82           80           80 
##        teams       design      fitness mercedesbenz   galaxygear 
##           79           77           77           77           75 
##        rumor         tech          got     motoactv     motorola 
##           74           74           72           71           68 
##       rumors        nokia          now         will      rumours 
##           67           67           65           64           64 
##       querer  application          cae       cuando   diferencia 
##           63           62           62           62           62 
##        entre          bao discontinued      android      vehicle 
##           62           61           61           60           60