Kori Aina
November 12, 2018
Extracting Tweets
Retrieve tweets from Twitter
# Load packages
library(rtweet)
library(tidyverse)# Twitter authentication
create_token(
app = "behumble_please",
consumer_key = consumer_key,
consumer_secret = consumer_secret,
access_token = access_token,
access_secret = access_secret)## <Token>
## <oauth_endpoint>
## request: https://api.twitter.com/oauth/request_token
## authorize: https://api.twitter.com/oauth/authenticate
## access: https://api.twitter.com/oauth/access_token
## <oauth_app> behumble_please
## key: OakS8ZIhrXK0l30ZZ9lBXlKxT
## secret: <hidden>
## <credentials> oauth_token, oauth_token_secret
## ---Note that the echo = FALSE parameter was added to the code chunk to prevent printing of the R code that generated the plot.
# Retrieve tweets
tweets <- search_tweets("#PKM", n = 1000, tweet_mode="extended")## Searching for tweets...## Finished collecting tweets!tweets <- distinct(tweets, text, .keep_all=TRUE)Tweets Description
## plot time series of tweets
ts_plot(tweets, "3 hours") +
theme_minimal() +
theme(plot.title = ggplot2::element_text(face = "bold")) +
labs(
x = NULL, y = NULL,
title = "Frequency of #Knowledges Twitter statuses from past 9 days",
subtitle = "Twitter status (tweet) counts aggregated using 3 hours",
caption = "\nSource: Data collected from Twitter's REST API via rtweet"
)
tail(tweets, 20)## # A tibble: 20 x 88
## user_id status_id created_at screen_name text source
## <chr> <chr> <dttm> <chr> <chr> <chr>
## 1 365680~ 10610385~ 2018-11-09 23:31:08 RogueGunn from~ Insta~
## 2 365680~ 10595657~ 2018-11-05 21:58:44 RogueGunn @Reg~ Insta~
## 3 811722~ 10610307~ 2018-11-09 23:00:27 TheBrianHo~ "Whi~ Buffer
## 4 884343~ 10608621~ 2018-11-09 11:50:14 umeadipat Toda~ Twitt~
## 5 302142~ 10608121~ 2018-11-09 08:31:39 wyborcza3m~ Szyk~ Twitt~
## 6 200480~ 10606616~ 2018-11-08 22:33:39 iamstanley~ Have~ Twitt~
## 7 195496~ 10603952~ 2018-11-08 04:55:14 mustajar3 "OTW~ Faceb~
## 8 951091~ 10602755~ 2018-11-07 20:59:20 NigeriaCap~ "@Mo~ Twitt~
## 9 162705~ 10601818~ 2018-11-07 14:46:55 GentleOddy A vo~ Twitt~
## 10 976416~ 10598374~ 2018-11-06 15:58:30 inxpirius By @~ Twitt~
## 11 174905~ 10594853~ 2018-11-05 16:39:36 juandoming netw~ Scoop~
## 12 160906~ 10598039~ 2018-11-06 13:45:18 Axel_Fisch~ "#Pa~ Insta~
## 13 111474~ 10596088~ 2018-11-06 00:50:21 Mik3Limon "@pa~ Twitt~
## 14 689976~ 10595953~ 2018-11-05 23:56:37 bowdenarti~ As #~ Twitt~
## 15 907764~ 10594040~ 2018-11-05 11:16:31 enymariani "Eva~ Insta~
## 16 988100~ 10592027~ 2018-11-04 21:56:24 whatacomeb~ Qiya~ Twitt~
## 17 196803~ 10591779~ 2018-11-04 20:17:59 PortalAcon~ "Um ~ Faceb~
## 18 105033~ 10583099~ 2018-11-02 10:48:47 JussiMozo "Wor~ Twitt~
## 19 716125~ 10584646~ 2018-11-02 21:03:29 EzeAsukwu @cho~ Twitt~
## 20 101369~ 10583682~ 2018-11-02 14:40:30 tomaszkoni~ "Prz~ Twitt~
## # ... with 82 more variables: display_text_width <dbl>,
## # reply_to_status_id <chr>, reply_to_user_id <chr>,
## # reply_to_screen_name <chr>, is_quote <lgl>, is_retweet <lgl>,
## # favorite_count <int>, retweet_count <int>, hashtags <list>,
## # symbols <list>, urls_url <list>, urls_t.co <list>,
## # urls_expanded_url <list>, media_url <list>, media_t.co <list>,
## # media_expanded_url <list>, media_type <list>, ext_media_url <list>,
## # ext_media_t.co <list>, ext_media_expanded_url <list>,
## # ext_media_type <chr>, mentions_user_id <list>,
## # mentions_screen_name <list>, lang <chr>, quoted_status_id <chr>,
## # quoted_text <chr>, quoted_created_at <dttm>, quoted_source <chr>,
## # quoted_favorite_count <int>, quoted_retweet_count <int>,
## # quoted_user_id <chr>, quoted_screen_name <chr>, quoted_name <chr>,
## # quoted_followers_count <int>, quoted_friends_count <int>,
## # quoted_statuses_count <int>, quoted_location <chr>,
## # quoted_description <chr>, quoted_verified <lgl>,
## # retweet_status_id <chr>, retweet_text <chr>,
## # retweet_created_at <dttm>, retweet_source <chr>,
## # retweet_favorite_count <int>, retweet_retweet_count <int>,
## # retweet_user_id <chr>, retweet_screen_name <chr>, retweet_name <chr>,
## # retweet_followers_count <int>, retweet_friends_count <int>,
## # retweet_statuses_count <int>, retweet_location <chr>,
## # retweet_description <chr>, retweet_verified <lgl>, place_url <chr>,
## # place_name <chr>, place_full_name <chr>, place_type <chr>,
## # country <chr>, country_code <chr>, geo_coords <list>,
## # coords_coords <list>, bbox_coords <list>, status_url <chr>,
## # name <chr>, location <chr>, description <chr>, url <chr>,
## # protected <lgl>, followers_count <int>, friends_count <int>,
## # listed_count <int>, statuses_count <int>, favourites_count <int>,
## # account_created_at <dttm>, verified <lgl>, profile_url <chr>,
## # profile_expanded_url <chr>, account_lang <chr>,
## # profile_banner_url <chr>, profile_background_url <chr>,
## # profile_image_url <chr>Text Cleaning
library(tm)## Loading required package: NLP##
## Attaching package: 'NLP'## The following object is masked from 'package:ggplot2':
##
## annotateBuild corpus
# build a corpus, and specify the source to be character vectors
myCorpus <- Corpus(VectorSource(tweets$text))
# convert to lower case
myCorpus <- tm_map(myCorpus, content_transformer(tolower))## Warning in tm_map.SimpleCorpus(myCorpus, content_transformer(tolower)):
## transformation drops documents# remove URLs
removeURL <- function(x) gsub("http[^[:space:]]*", "", x)
myCorpus <- tm_map(myCorpus, content_transformer(removeURL))## Warning in tm_map.SimpleCorpus(myCorpus, content_transformer(removeURL)):
## transformation drops documents# remove anything other than English letters or space
removeNumPunct <- function(x) gsub("[^[:alpha:][:space:]]*", "", x)
myCorpus <- tm_map(myCorpus, content_transformer(removeNumPunct))## Warning in tm_map.SimpleCorpus(myCorpus,
## content_transformer(removeNumPunct)): transformation drops documents# remove stopwords
myStopwords <- c(setdiff(stopwords('english'), c("r", "big")), "use", "see", "used", "via", "amp", "indihome")
stopwords_id <- read.table('E:/stopwords-id.txt', header = FALSE)
myStopwords <- c(myStopwords, as.matrix(stopwords_id$V1), "hi", "yg")
myCorpus <- tm_map(myCorpus, removeWords, myStopwords)## Warning in tm_map.SimpleCorpus(myCorpus, removeWords, myStopwords):
## transformation drops documents# remove extra whitespace
myCorpus <- tm_map(myCorpus, stripWhitespace)## Warning in tm_map.SimpleCorpus(myCorpus, stripWhitespace): transformation
## drops documents# keep a copy for stem completion later
myCorpusCopy <- myCorpusFrequent Words
Build Term Document Matrix
tdm <- TermDocumentMatrix(myCorpus, control = list(wordLengths = c(1, Inf)))tdm## <<TermDocumentMatrix (terms: 502, documents: 52)>>
## Non-/sparse entries: 933/25171
## Sparsity : 96%
## Maximal term length: 27
## Weighting : term frequency (tf)Top Frequent Terms
freq.terms <- findFreqTerms(tdm, lowfreq = 20)freq.terms[1:50]## [1] "pkm" NA NA NA NA NA NA NA NA NA NA
## [12] NA NA NA NA NA NA NA NA NA NA NA
## [23] NA NA NA NA NA NA NA NA NA NA NA
## [34] NA NA NA NA NA NA NA NA NA NA NA
## [45] NA NA NA NA NA NAterm.freq <- rowSums(as.matrix(tdm))
term.freq <- subset(term.freq, term.freq >= 10)
df <- data.frame(term = names(term.freq), freq = term.freq)ggplot(df,aes(x=term, y=freq)) + geom_bar(stat="identity") +
xlab("Terms") + ylab("Count") + coord_flip() +
theme(axis.text=element_text(size=7))
Wordcloud
Build Wordcloud
library(wordcloud)## Loading required package: RColorBrewerm <- as.matrix(tdm)
# calculate the frequency of words and sort it by frequency
word.freq <- sort(rowSums(m), decreasing = T)
# colors
pal <- brewer.pal(9, "BuGn")[-(1:4)]wordcloud(words = names(word.freq), freq = word.freq, min.freq = 3,
random.order = F, colors = pal)