—title: “Twitter_Text” author: “Ganis Ardhaning Saputri” date: “November 12, 2018” output: html_document —
Text Mining
Analytics Twitter “Surabaya”
Ganis Ardhaning Saputri_06211540000056
Retrieve Tweets from Twitter
#load packages
library(rtweet)
library(tidyverse)Twitter Autentication
# Twitter authentication
create_token(
app = "my_twitter_research_app",
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> my_twitter_research_app
## key: Lz7QKeXfeJWTM4KBDk4Qe7Uoy
## secret: <hidden>
## <credentials> oauth_token, oauth_token_secret
## ---# Retrieve tweets
tweets <- search_tweets("#SepuluhNopember", n = 1000, langs="en", tweet_mode="extended")## Searching for tweets...## Finished collecting tweets!Tweets Description
## plot time series of tweets
ts_plot(tweets, "3 hours") +
ggplot2::theme_minimal() +
ggplot2::theme(plot.title = ggplot2::element_text(face = "bold")) +
ggplot2::labs(
x = NULL, y = NULL,
title = "Frequency of #SepuluhNopember Twitter statuses from past 9 days",
subtitle = "Twitter status (tweet) counts aggregated using three-hour intervals",
caption = "\nSource: Data collected from Twitter's REST API via rtweet"
)
head(tweets)## # A tibble: 6 x 88
## user_id status_id created_at screen_name text source
## <chr> <chr> <dttm> <chr> <chr> <chr>
## 1 348241~ 10616113~ 2018-11-11 13:27:21 ankulon "#Re~ Insta~
## 2 970696~ 10612275~ 2018-11-10 12:02:11 Mutiaramil~ "Har~ Twitt~
## 3 178350~ 10612006~ 2018-11-10 10:15:37 noviadwipe~ "Har~ Twitt~
## 4 101665~ 10611952~ 2018-11-10 09:54:01 dadangonly_ "Har~ Twitt~
## 5 823255~ 10610726~ 2018-11-10 01:46:43 rudy46tuban "Pad~ Twitt~
## 6 110104~ 10610723~ 2018-11-10 01:45:33 AdibArinan~ "Sel~ Twitt~
## # ... with 82 more variables: display_text_width <dbl>,
## # reply_to_status_id <lgl>, reply_to_user_id <lgl>,
## # reply_to_screen_name <lgl>, 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':
##
## annotate## Build 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")
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: 56, documents: 8)>>
## Non-/sparse entries: 106/342
## Sparsity : 76%
## Maximal term length: 19
## Weighting : term frequency (tf)Top Frequent Terms
freq.terms <- findFreqTerms(tdm, lowfreq = 20)freq.terms[1:50]## [1] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
## [24] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
## [47] NA NA NA NAterm.freq <- rowSums(as.matrix(tdm))
term.freq <- subset(term.freq, term.freq >= 1000)
df <- data.frame(term = names(term.freq), freq = term.freq)ggplot2::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 = 300,
random.order = F, colors = pal)## Warning in wordcloud(words = names(word.freq), freq = word.freq, min.freq =
## 300, : sepuluhnopember could not be fit on page. It will not be plotted.