Last active
January 18, 2023 18:26
-
-
Save CateGitau/05e6ff80b2a3aaa58236067811cee44e to your computer and use it in GitHub Desktop.
Analyzing twitter data using R
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #install required packages | |
| install.packages("twitteR") | |
| install.packages("RCurl") | |
| install.packages("httr") | |
| install.packages("devtools") | |
| install.packages(toInstall, repos = "http://cran.r-project.org") | |
| library(devtools) | |
| #Load necessary packages | |
| library(twitteR) | |
| library(RCurl) | |
| library(base64enc) | |
| # XXX: Go to http://dev.twitter.com/apps/new to create an app and get values | |
| # for these credentials, which you'll need to provide in place of these | |
| # empty string values that are defined as placeholders. | |
| # See https://dev.twitter.com/docs/auth/oauth for more information | |
| # on Twitter's OAuth implementation. | |
| Access_token <- "" | |
| Access_token_secret <- "" | |
| consumer_key <- "" | |
| consumer_secret <- "" | |
| #Calling twitteR OAuth function | |
| setup_twitter_oauth(consumer_key,consumer_secret,Access_token,Access_token_secret) | |
| #getting timeline data on ma3Route | |
| tweets <- userTimeline("name", n=3200, maxID=NULL, sinceID=NULL, includeRts=TRUE) | |
| #convert the tweets into a df | |
| tweets.df <-twListToDF(tweets) | |
| dim(tweets.df) | |
| library(tm) | |
| library(stringr) | |
| #build a corpus and specify the source to be character of vectors | |
| #a corpus is a collection of written texts | |
| myCorpus <- Corpus(VectorSource(tweets.df$text)) | |
| myCorpus <- tm_map(myCorpus, function(x) iconv(enc2utf8(x), sub = "byte")) | |
| #convert myCorpus into lowercase | |
| myCorpus <- tm_map(myCorpus, content_transformer(tolower)) | |
| #remove punctuation | |
| myCorpus <- tm_map(myCorpus, removePunctuation) | |
| #remove numbers | |
| myCorpus <- tm_map(myCorpus, removeNumbers) | |
| Textprocessing <- function(x) | |
| {gsub("http[[:alnum:]]*",'', x) | |
| gsub('http\\S+\\s*', '', x) ## Remove URLs | |
| gsub('\\b+RT', '', x) ## Remove RT | |
| gsub('#\\S+', '', x) ## Remove Hashtags | |
| gsub('@\\S+', '', x) ## Remove Mentions | |
| gsub('[[:cntrl:]]', '', x) ## Remove Controls and special characters | |
| gsub("\\d", '', x) ## Remove Controls and special characters | |
| gsub('[[:punct:]]', '', x) ## Remove Punctuations | |
| gsub("^[[:space:]]*","",x) ## Remove leading whitespaces | |
| gsub("[[:space:]]*$","",x) ## Remove trailing whitespaces | |
| gsub(' +',' ',x) ## Remove extra whitespaces | |
| } | |
| myCorpus <- tm_map(myCorpus,Textprocessing) | |
| # remove extra whitespace | |
| myCorpus <- tm_map(myCorpus, stripWhitespace) | |
| #add stopwords | |
| #stopwords are words which do not contain much significance. | |
| #These words are usually filtered out because they return vast amount of unnecessary information. | |
| mystopwords <- c(stopwords("english"),"rt","íí","get","like","just","yes","know","will","good","day","people") | |
| #remove stopwords | |
| myCorpus <- tm_map(myCorpus,removeWords,mystopwords) | |
| #copy of corpus | |
| myCorpus_copy <- myCorpus | |
| #stem words | |
| myCorpus <- tm_map(myCorpus,stemDocument) | |
| for (i in c(1:2, 3163)){ | |
| cat(paste0("[", i, "] ")) | |
| writeLines(strwrap(as.character(myCorpus_copy[[i]]), 60))} | |
| # stemCompletion2 <- function(x, dictionary){ | |
| # x <- unlist(strsplit(as.character(x), " ")) | |
| # # Unexpectedly, stemCompletion completes an empty string to | |
| # # a word in dictionary. Remove empty string to avoid above issue. | |
| # x <- x[x != ""] | |
| # x <- stemCompletion(x, dictionary=dictionary) | |
| # x <- paste(x, sep="", collapse=" ") | |
| # PlainTextDocument(stripWhitespace(x)) | |
| # } | |
| myCorpus <- tm_map(myCorpus, stemCompletion, dictionary=myCorpus_copy) | |
| #myCorpus <- lapply(myCorpus, stemCompletion2, dictionary=myCorpus_copy) | |
| myCorpus <- Corpus(VectorSource(myCorpus)) | |
| myCorpus <- iconv(x = myCorpus,"latin1","ASCII",sub = "") | |
| tdm <- TermDocumentMatrix(myCorpus_copy,control = list(wordlengths = c(1,Inf))) | |
| tdm | |
| #inspect frequent words | |
| freq.terms <- findFreqTerms(tdm, lowfreq = 50) | |
| View(freq.terms) | |
| termFreq <- rowSums(as.matrix(tdm)) | |
| termFreq <- subset(termFreq, termFreq >=20) | |
| df <- data.frame(term = names(termFreq), freq = termFreq) | |
| View(df) | |
| #visualize frequent terms | |
| library(ggplot2) | |
| #visualize frequent terms | |
| library(ggplot2) | |
| ggplot(df,aes(x = reorder(df$term, +df$freq), y = freq, fill=df$freq)) + geom_bar(stat = "identity") + | |
| scale_colour_gradientn(colors = terrain.colors(10)) + xlab("Terms") + ylab("Count") + coord_flip() | |
| #load required libraries | |
| library(wordcloud) | |
| library(wordcloud2) | |
| m <- as.matrix(tdm) | |
| # colors | |
| pal <- brewer.pal(9, "BuGn") | |
| pal <- pal[-(1:4)] | |
| #calculate the frequency of words as sort it by frequency | |
| word.freq <- sort(rowSums(m), decreasing = T) | |
| wordcloud2(df, color = "random-dark", backgroundColor = "white",figPath = "sev.png") | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Nice work, very useful code :)