This is an R Markdown Notebook. When you execute code within the notebook, the results appear beneath the code.

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')
# install.packages('plotly')

Clean data

library(readr)
gear <- read.csv("C:\\Users\\206429159\\Documents\\Rstudio\\Samsung Tweets1.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

health.words = scan('health_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, health.words, .progress='none')

## Loading required package: plyr

## Loading required package: stringr

## Loading required package: stringi

topic.mentioned = subset(topic.scores, score !=0)

N= nrow(topic.scores)
Nmentioned = nrow(topic.mentioned)

dftemp=data.frame(topic=c("Mentioned", "Not Mentioned"), 
                  number=c(Nmentioned,N-Nmentioned))

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

Word cloud

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)

healthTweets = subset(topic.scores, score !=0)$text

corpus = Corpus(VectorSource(healthTweets))
# 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) 

#remove the top words which donât generate insights such as "the", "a", "and", etc.
# Here â1:9â is the first 9 words in the list we want to remove 
# word_freqs = word_freqs[-(1:9)]  #H

# 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$word, 50), head(dm$freq, 50), random.order=FALSE, colors=brewer.pal(8, "Dark2"))

#check top 50 most mentioned words
head(word_freqs, 20)

##    watch    apple   pebble  samsung      new   iwatch   fitbit    force 
##     3285     2856     2695     2679     2615     2559     2394     2173 
## smawatch   galaxy      sma      toq     sony qualcomm      win     just 
##     2103     1349     1093     1089     1031     1028      863      843 
##  fitness   iphone     ipad     next 
##      803      768      725      672

CS695: Topic Analysis R Notebook

Richard S.

Install required packages

Clean data

Topic Analysis

Word cloud