Sentiment Analysis R Notebook

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

sport.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, sport.words, .progress='none')

## Loading required package: plyr

## Loading required package: stringr

## Loading required package: stringi

## Loading required package: plyr
## Loading required package: stringr
## Loading required package: stringi
sportsTweets = subset(topic.scores, score !=0)$text


# Sentiment Analysis

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(sportsTweets, 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

## 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

# Pie chart for positive, negative and neutral tweets

sentiment.positive = subset(sentiment.scores, score >0)
sentiment.negative = subset(sentiment.scores, score <0)
sentiment.neutral = subset(sentiment.scores, score ==0)

N= nrow(sentiment.scores)
Npositive = nrow(sentiment.positive)
NNegative = nrow(sentiment.negative)
NNeutral =  nrow(sentiment.neutral)

dftemp=data.frame(topic=c("Positive", "Negative","Neutral"), 
                  number=c(Npositive,NNegative,NNeutral))

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