CS695: Topic Analysis R Notebook

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

#install the necessary packages
# install.packages("readr")
# install.packages("plyr")
# install.packages("stringr")
# install.packages("stringi")
# install.packages("magrittr")
# install.packages("dplyr")

library(readr)
gear <- read.csv("Samsung Tweets.csv", comment.char="#")
geartweets <- gear$tweettext
#********************************************
#         Word Cloud
#********************************************
#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=';')

Read 368 items

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(tweets, sports.words, .progress='none')
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)
p <- plot_ly(data=dftemp, labels = ~topic, values = ~number, type = 'pie') %>%
  layout(title = 'Pie Chart of Mentions',
         xaxis = list(showgrid = FALSE, zeroline = FALSE, showticklabels = FALSE),
         yaxis = list(showgrid = FALSE, zeroline = FALSE, showticklabels = FALSE))
p