title: “Sentiment Analysis on Political Leaders via Twitter” author: “Emre Toros” date: “9 September 2016” output: html_document
This is a project on sentiment analysis of the tweets. Aim is to score the negative and/or positive tweets on Putin, in order to understand the public opnion on Putin via twitter. The sample consists of the last 500 tweets mentioning Vladimir Putin in English. You can replicate the same analysis by changing the twitter handle to the leader you want
The reading materials used in this document are as follows: 1. https://cran.r-project.org/web/packages/twitteR/twitteR.pdf 2. https://dl.dropboxusercontent.com/u/4839225/twitter%20text%20mining%20with%20R.pdf 3. https://www.cs.uic.edu/~liub/FBS/sentiment-analysis.html 4. https://dev.twitter.com/oauth/overview/introduction
The neccesary packages
library(twitteR)
library(tm)## Loading required package: NLPlibrary(plyr)##
## Attaching package: 'plyr'## The following object is masked from 'package:twitteR':
##
## idlibrary(stringr)
library(sjPlot)TwitteR app authorization, the real values are masked, you should get your own values, refer to reading material 1 page 13
setup_twitter_oauth("5z59VX7Ba4FMboyXZqEH2yqK7", "9D8l6HjFggTQT1mnM3cGlGIYAf01lerhDuAERTvGV7iKkHfuod", access_token = "83306745-B0eaQ9aFO9Og5KpjurHObOnkwibO4Y5Xd5ipkkriy", access_secret = "WZIHeROVTgcBSKNFOhmFGrF4Ogvaxql7TRnE0I9I8uyoQ")## [1] "Using direct authentication"Collecting tweets on Putin, you can change “n”" to the number of tweets that you want
putin <- searchTwitter("@PutinRF_Eng", lang="en", n=500)Extracting the tweet text
putin.text = laply(putin, function(t) t$getText() )lexicon for sentiments
hu.liu.pos <- scan("D:/emre/SkyDrive/makale/R/opinion-lexicon-English/positive-words.txt",
what="character", comment.char=";")
hu.liu.neg <- scan("D:/emre/SkyDrive/makale/R/opinion-lexicon-English/negative-words.txt",
what="character", comment.char=";")
pos.words <- c(hu.liu.pos)
neg.words <- c(hu.liu.neg)setting the score.sentiment function, unique function you cannot find it in any package
score.sentiment <- function(sentences, pos.words, neg.words, .progress='none')
{
require(plyr)
require(stringr)
# we got a vector of sentences. plyr will handle a list
# or a vector as an "l" for us
# we want a simple array ("a") 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)
}Analysis on Putin
putin.scores <- score.sentiment(putin.text, pos.words,neg.words, .progress='text')##
|
| | 0%
|
| | 1%
|
|= | 1%
|
|= | 2%
|
|== | 2%
|
|== | 3%
|
|== | 4%
|
|=== | 4%
|
|=== | 5%
|
|==== | 5%
|
|==== | 6%
|
|==== | 7%
|
|===== | 7%
|
|===== | 8%
|
|====== | 9%
|
|====== | 10%
|
|======= | 10%
|
|======= | 11%
|
|======== | 12%
|
|======== | 13%
|
|========= | 13%
|
|========= | 14%
|
|========= | 15%
|
|========== | 15%
|
|========== | 16%
|
|=========== | 16%
|
|=========== | 17%
|
|=========== | 18%
|
|============ | 18%
|
|============ | 19%
|
|============= | 19%
|
|============= | 20%
|
|============= | 21%
|
|============== | 21%
|
|============== | 22%
|
|=============== | 22%
|
|=============== | 23%
|
|=============== | 24%
|
|================ | 24%
|
|================ | 25%
|
|================= | 25%
|
|================= | 26%
|
|================= | 27%
|
|================== | 27%
|
|================== | 28%
|
|=================== | 29%
|
|=================== | 30%
|
|==================== | 30%
|
|==================== | 31%
|
|===================== | 32%
|
|===================== | 33%
|
|====================== | 33%
|
|====================== | 34%
|
|====================== | 35%
|
|======================= | 35%
|
|======================= | 36%
|
|======================== | 36%
|
|======================== | 37%
|
|======================== | 38%
|
|========================= | 38%
|
|========================= | 39%
|
|========================== | 39%
|
|========================== | 40%
|
|========================== | 41%
|
|=========================== | 41%
|
|=========================== | 42%
|
|============================ | 42%
|
|============================ | 43%
|
|============================ | 44%
|
|============================= | 44%
|
|============================= | 45%
|
|============================== | 45%
|
|============================== | 46%
|
|============================== | 47%
|
|=============================== | 47%
|
|=============================== | 48%
|
|================================ | 49%
|
|================================ | 50%
|
|================================= | 50%
|
|================================= | 51%
|
|================================== | 52%
|
|================================== | 53%
|
|=================================== | 53%
|
|=================================== | 54%
|
|=================================== | 55%
|
|==================================== | 55%
|
|==================================== | 56%
|
|===================================== | 56%
|
|===================================== | 57%
|
|===================================== | 58%
|
|====================================== | 58%
|
|====================================== | 59%
|
|======================================= | 59%
|
|======================================= | 60%
|
|======================================= | 61%
|
|======================================== | 61%
|
|======================================== | 62%
|
|========================================= | 62%
|
|========================================= | 63%
|
|========================================= | 64%
|
|========================================== | 64%
|
|========================================== | 65%
|
|=========================================== | 65%
|
|=========================================== | 66%
|
|=========================================== | 67%
|
|============================================ | 67%
|
|============================================ | 68%
|
|============================================= | 69%
|
|============================================= | 70%
|
|============================================== | 70%
|
|============================================== | 71%
|
|=============================================== | 72%
|
|=============================================== | 73%
|
|================================================ | 73%
|
|================================================ | 74%
|
|================================================ | 75%
|
|================================================= | 75%
|
|================================================= | 76%
|
|================================================== | 76%
|
|================================================== | 77%
|
|================================================== | 78%
|
|=================================================== | 78%
|
|=================================================== | 79%
|
|==================================================== | 79%
|
|==================================================== | 80%
|
|==================================================== | 81%
|
|===================================================== | 81%
|
|===================================================== | 82%
|
|====================================================== | 82%
|
|====================================================== | 83%
|
|====================================================== | 84%
|
|======================================================= | 84%
|
|======================================================= | 85%
|
|======================================================== | 85%
|
|======================================================== | 86%
|
|======================================================== | 87%
|
|========================================================= | 87%
|
|========================================================= | 88%
|
|========================================================== | 89%
|
|========================================================== | 90%
|
|=========================================================== | 90%
|
|=========================================================== | 91%
|
|============================================================ | 92%
|
|============================================================ | 93%
|
|============================================================= | 93%
|
|============================================================= | 94%
|
|============================================================= | 95%
|
|============================================================== | 95%
|
|============================================================== | 96%
|
|=============================================================== | 96%
|
|=============================================================== | 97%
|
|=============================================================== | 98%
|
|================================================================ | 98%
|
|================================================================ | 99%
|
|=================================================================| 99%
|
|=================================================================| 100%Plotting the scores
sjp.frq(putin.scores$score)