Pilih kopi Starbuck apa enaknya?

Pilih kopi Starbuck apa enaknya?

Untuk menjawab pertanyaan di atas, akan kami coba menganalisa data hasil scrapping dari laman twitter Starbuck Indonesia  @SbuxIndonesia(23 Feb 2019, jam 10 wib). Hasil analisa akan dibagi menjadi: 1. Klasifikasi emosi, 2. Klasifikasi polaritas, 3. Analisa Corpus.

Tentunya analisa ini masih terbatas pada quota free yang diberikan oleh twitter, tapi sudah bisa memberi gambaran singkat tentang persepsi  umumnya masyarakat Indonesia terhadap Starbuck, untuk  mencapai hasil yang maximal tinggal mengajukan quota yang diinginkat ke twitter.

Berikut saya berikan script R nya:

Tb1

Tb2

Tb3

#---Install library

library(plyr)

library(ggplot2)

library(wordcloud)

library(RColorBrewer)

library(httr)

library(slam)

library(mime)

library(R6)

library(twitteR)

library(bit)

library(bit64)

library(rjson)

library(DBI)

library(tm)

library(Rstem)

library(NLP)

library(sentiment)

library(Rcpp)

#---1.Connect to Twitter

#Enter the authentication details below

# Authenticate with Twitter

api_key <- "xxxxxxxxxx"

api_secret <- " xxxxxxxxxx"

access_token <- " xxxxxxxxxx "

access_token_secret <- " xxxxxxxxxx "

setup_twitter_oauth(api_key, api_secret, access_token, access_token_secret)

#---2.Harvest some tweets

some_tweets = searchTwitter("@SbuxIndonesia", n=500, lang="en")

# get the text

some_txt = sapply(some_tweets, function(x) x$getText())

#--- 3.Prepare text for sentiment analysis

# remove retweet entities

some_txt = gsub("(RT|via)((?:\\b\\W*@\\w+)+)", "", some_txt)

# remove at people

some_txt = gsub("@\\w+", "", some_txt)

# remove punctuation

some_txt = gsub("[[:punct:]]", "", some_txt)

# remove numbers

some_txt = gsub("[[:digit:]]", "", some_txt)

# remove html links

some_txt = gsub("http\\w+", "", some_txt)

# remove unnecessary spaces

some_txt = gsub("[ \t]{2,}", "", some_txt)

some_txt = gsub("^\\s+|\\s+$", "", some_txt)

# define "tolower error handling" function

try.error = function(x)

{

   # create missing value

   y = NA

   # tryCatch error

   try_error = tryCatch(tolower(x), error=function(e) e)

   # if not an error

   if (!inherits(try_error, "error"))

   y = tolower(x)

   # result

   return(y)

}

# lower case using try.error with sapply

some_txt = sapply(some_txt, try.error)

# remove NAs in some_txt

some_txt = some_txt[!is.na(some_txt)]

names(some_txt) = NULL

#---4. Perform sentiment analysis

#Please note that the classifying the polarity and emotion of the tweets may take a few minutes

# classify emotion

class_emo = classify_emotion(some_txt, algorithm="bayes", prior=1.0)

# get emotion best fit

emotion = class_emo[,7]

# substitute NA's by "unknown"

emotion[is.na(emotion)] = "unknown"

# classify polarity

class_pol = classify_polarity(some_txt, algorithm="bayes")

# get polarity best fit

polarity = class_pol[,4]

#---5.Create a data frame in order plot the results

# data frame with results

sent_df = data.frame(text=some_txt, emotion=emotion,

polarity=polarity, stringsAsFactors=FALSE)

# sort data frame

sent_df = within(sent_df, emotion, polarity)

head(sent_df)                                                        

                                                            

#text               

#congratulationsfor winning the champions league title in milan uclfinal

#emotion polarity

#unknown positive

#---6. Plot the emotions and polarity of the tweets

# plot distribution of emotions

p <- ggplot(sent_df, aes(x = emotion)) +

  geom_bar(aes(y = ..count.., fill = emotion)) +

  scale_fill_brewer(palette = "Dark2") +

  labs(x = "emotion categories", y = "number of comments") +

  labs(title = "Analisa Sentimen Twitter Starbuck Indonesia\n(classification by emotion)",

     plot.title = element_text(size=12))+

  theme_bw()#ok

#---7. Plot distribution of polarity

p1 <- ggplot(sent_df, aes(x=polarity)) +

  geom_bar(aes(y=..count.., fill=polarity)) +

  scale_fill_brewer(palette="RdGy") +

  labs(x="polarity categories", y="number of tweets") +

  labs(title = "Analisa Sentimen Twitter Starbuck Indonesia \n(classification by polarity)",

       plot.title = element_text(size=12)) +

  theme_dark()#ok

# separating text by emotion

emos = levels(factor(sent_df$emotion))

nemo = length(emos)

emo.docs = rep("", nemo)

for (i in 1:nemo)

{

tmp = some_txt[emotion == emos[i]]

emo.docs[i] = paste(tmp, collapse="")

}

# remove stopwords

emo.docs = removeWords(emo.docs, stopwords("english"))

# ---8.Create corpus

corpus = Corpus(VectorSource(emo.docs))

tdm = TermDocumentMatrix(corpus)

tdm = as.matrix(tdm)

colnames(tdm) = emos

# comparison word cloud

comparison.cloud(tdm, colors = brewer.pal(nemo, "Dark2"), scale = c(3,.5),

                 random.order = FALSE, title.size = 1.5)

Kesimpulan:

1.  Dari Tb1 terlihat, starbuck Indonesia banyak yang menyukai  dan

nyaman  untuk berlama lama di Starbuck ,data(joy = 80), meskipun masih ada juga yang kurang cocok terlihat dari data(sadness=20).  Bagi starbuck ada tantangan karena ada data yang belum dimengerti, dan tentu perlu dipelajari lebih dalam(unknow hampir 60),  starbuck jangan berbangga diri dulu karena  nilai  surprise cuma kira kira 5.

2. Dari Tb2, dari table polaritas, menegaskan table 1, tanggapan positive terhadap Starbuck Indonesia demikian besar(nilainya hampir 80), meskipun tanggapan negative juga  tidak boleh diremehkan.

3. Dari Tb3 , memang tidak dipungkiri sampai saat ini “taste” Starbuck Indonesia masih menjadi factor utama.

Referensi:

1.       Tokopedia vs Bukalapak

2.       Rstudio

3.       Library

4.       https://developer.twitter.com/en/apps