week5

Clean data

library(readr)

## Warning: package 'readr' was built under R version 3.4.3

gear <- read.csv("C:\\Users\\Xiayang Xiao\\Downloads\\Samsung Tweets(1).csv", row.names=1, sep=";")
geartweets <- gear$tweettext


clean.text = function(x)
{
  
  x = tolower(x)
 
  x = gsub("rt", "", x)
  
  x = gsub("@\\w+", "", x)
 
  x = gsub("[[:punct:]]", "", x)

  x = gsub("[[:digit:]]", "", x)

  x = gsub("http\\w+", "", x)

  x = gsub("[ |\t]{2,}", "", x)

  x = gsub("^ ", "", x)

  x = gsub(" $", "", x)
  return(x)
}


geartweets = clean.text(geartweets)

Sentiment Analysis

pos.words = scan('C:\\Users\\Xiayang Xiao\\Downloads\\positive-words.txt', what='character', comment.char=';')
neg.words = scan('C:\\Users\\Xiayang Xiao\\Downloads\\negative-words.txt', what='character', comment.char=';')

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


require(plyr)

## Loading required package: plyr

## Warning: package 'plyr' was built under R version 3.4.3

require(stringr)

## Loading required package: stringr

## Warning: package 'stringr' was built under R version 3.4.3

require(stringi)

## Loading required package: stringi

score.sentiment = function(sentences, pos.words, neg.words, .progress='none')
{
  
 
  scores = laply(sentences, function(sentence, pos.words, neg.words) {
    
    
    sentence = gsub('[[:punct:]]', '', sentence)
    sentence = gsub('[[:cntrl:]]', '', sentence)
    sentence = gsub('\\d+', '', sentence)
    sentence = tolower(sentence)
    word.list = str_split(sentence, '\\s+')
    words = unlist(word.list)
    pos.matches = match(words, pos.words)
    neg.matches = match(words, neg.words)
    pos.matches = !is.na(pos.matches)
    neg.matches = !is.na(neg.matches)
    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')

score <- sentiment.scores$score

library(plotly)

## Warning: package 'plotly' was built under R version 3.4.3

## Loading required package: ggplot2

## Warning: package 'ggplot2' was built under R version 3.4.3

## 
## 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

## Warning: package 'bindrcpp' was built under R version 3.4.3

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))
tdm = TermDocumentMatrix(
  corpus,
  control = list(
    wordLengths=c(3,20),
    removePunctuation = TRUE,
    stopwords = c("the", "a", stopwords("english")),
    removeNumbers = TRUE, tolower = TRUE) )


tdm = as.matrix(tdm)

word_freqs = sort(rowSums(tdm), decreasing=TRUE) 
word_freqs = word_freqs[-(1:12)]
dm = data.frame(word=names(word_freqs), freq=word_freqs)


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

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

pie chart

positive = subset(sentiment.scores, score > 0)
negtive  = subset(sentiment.scores, score < 0)
neutral = subset(sentiment.scores, score = 0)
No.positive = nrow(positive)
No.negtive = nrow(negtive)
No.neutral= nrow(neutral)
dftemp=data.frame(topic=c("positive", "negtive","neutral"), 
                  number=c(No.positive,No.negtive,No.neutral))

library(plotly)

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