Memproses teks Twitter

Menganalisis Data Media Sosial dengan R

Vivek Vijayaraghavan

Data Science Coach

Gambaran pelajaran

  • Mengapa memproses teks tweet?
  • Langkah pemrosesan teks tweet
    • menghapus informasi berlebih
    • mengonversi teks menjadi korpus
    • menghapus stop word
Menganalisis Data Media Sosial dengan R

Mengapa memproses teks tweet?

  • Teks tweet tidak terstruktur, bising, dan mentah
  • Mengandung emotikon, URL, angka
  • Perlu pembersihan untuk analisis dan hasil andal
Menganalisis Data Media Sosial dengan R

Langkah pemrosesan teks

Langkah1: Hapus informasi berlebih

Menganalisis Data Media Sosial dengan R

Langkah pemrosesan teks

Langkah2: Konversi teks menjadi korpus

Menganalisis Data Media Sosial dengan R

Langkah pemrosesan teks

Langkah3: Ubah ke huruf kecil

Menganalisis Data Media Sosial dengan R

Langkah pemrosesan teks

Langkah4: Hapus stop word

Menganalisis Data Media Sosial dengan R

Ekstrak teks tweet

# Extract 1000 tweets on "Obesity" in English and exclude retweets
tweets_df <- search_tweets("Obesity", n = 1000, include_rts = F, lang = 'en')
# Extract the tweet texts and save it in a data frame
twt_txt <- tweets_df$text
Menganalisis Data Media Sosial dengan R

Ekstrak teks tweet

head(twt_txt, 3)
[1] "@WeeaUwU for real, obesity should not be praised like it is in today's society" 

[2] "Great work by @DosingMatters in @AJHPOfficial on \"Vancomycin Vd estimation in 
adults with class III obesity\". As we continue to study/learn more about dosing in 
large body weight pts, we see that it's not a simple, one size, one level estimate 
that works https://t.co/KkYPqS6JzG" 

[3] "The Scottish Government have an ambition to halve childhood obesity by 2030. 
This means reducing obesity prevalence in 2-15yo children in Scotland to 7%. 
\n\n\U0001f449 In 2018, this figure was 16%\n\nFind out more in our latest blog: 
https://t.co/FWp56QWjQc https://t.co/XBK8Je7F1A"
Menganalisis Data Media Sosial dengan R

Menghapus URL

# Remove URLs from the tweet text
library(qdapRegex)
twt_txt_url <- rm_twitter_url(twt_txt)
Menganalisis Data Media Sosial dengan R

Menghapus URL

twt_txt_url[1:3]
[1] "@WeeaUwU for real, obesity should not be praised like it is in today's society"

[2] "Great work by @DosingMatters in @AJHPOfficial on \"Vancomycin Vd estimation in  adults 
with class III obesity\". As we continue to study/learn more about dosing in large body 
weight pts, we see that it's not a simple, one size, one level estimate that works"

[3] "The Scottish Government have an ambition to halve childhood obesity by 2030. 
This means reducing obesity prevalence in 2-15yo children in Scotland to 7%. 
\U0001f449In 2018, this figure was 16% Find out more in our latest blog:"  
Menganalisis Data Media Sosial dengan R

Karakter khusus, tanda baca, dan angka

# Remove special characters, punctuation & numbers
twt_txt_chrs  <- gsub("[^A-Za-z]", " ", twt_txt_url)
Menganalisis Data Media Sosial dengan R

Karakter khusus, tanda baca, dan angka

twt_txt_chrs[1:3]
[1] " WeeaUwU for real  obesity should not be praised like it is in today s society"

[2] "Great work by  DosingMatters in  AJHPOfficial on  Vancomycin Vd estimation in 
adults with class III obesity   As we continue to study learn more about dosing in 
large body weight pts  we see that it s not a simple  one size  one level estimate 
that works"

[3] "The Scottish Government have an ambition to halve childhood obesity by       This 
means reducing obesity prevalence in     yo children in Scotland to       In       this 
figure was     Find out more in our latest blog "   
Menganalisis Data Media Sosial dengan R

Konversi ke korpus teks

# Convert to text corpus
library(tm)
twt_corpus <- twt_txt_chrs %>% 
                VectorSource() %>% 
                Corpus()
twt_corpus[[3]]$content
[1] "The Scottish Government have an ambition to halve childhood obesity by       
This means reducing obesity prevalence in     yo children in Scotland to       In  
     this figure was     Find out more in our latest blog "
Menganalisis Data Media Sosial dengan R

Konversi ke huruf kecil

  • Satu kata tidak boleh dihitung sebagai dua kata berbeda hanya karena perbedaan huruf besar-kecil
# Convert text corpus to lowercase
twt_corpus_lwr <- tm_map(twt_corpus, tolower) 
twt_corpus_lwr[[3]]$content
[1] "the scottish government have an ambition to halve childhood obesity by     this 
means reducing obesity prevalence in     yo children in scotland to       in    this 
figure was     find out more in our latest blog "
Menganalisis Data Media Sosial dengan R

Apa itu stop word?

  • Stop word adalah kata umum seperti a, an, and, but
# Common stop words in English
stopwords("english")

Stop word baku dalam bahasa Inggris

Menganalisis Data Media Sosial dengan R

Hapus stop word

  • Stop word perlu dihapus agar fokus pada kata penting
# Remove stop words from corpus
twt_corpus_stpwd <- tm_map(twt_corpus_lwr, removeWords, stopwords("english"))
twt_corpus_stpwd[[3]]$content

[1] " scottish government   ambition  halve childhood obesity         means 
reducing obesity prevalence      yo children  scotland                figure      
find     latest blog "
Menganalisis Data Media Sosial dengan R

Hapus spasi berlebih

  • Hapus spasi ganda untuk membuat korpus bersih
# Remove additional spaces
twt_corpus_final <- tm_map(twt_corpus_stpwd, stripWhitespace)
twt_corpus_final[[3]]$content
[1] " scottish government ambition halve childhood obesity means reducing obesity 
prevalence yo children scotland figure find latest blog "
Menganalisis Data Media Sosial dengan R

Ayo berlatih!

Menganalisis Data Media Sosial dengan R

Preparing Video For Download...