Analisis Sentimen Data Crowling Twitter
SAHRA MASDAR
2023-12-02
Panggil semua packages dengan fungsi library (nama_packages)
library(wordcloud)## Loading required package: RColorBrewerlibrary(tm)## Loading required package: NLPlibrary(textclean)
library(tidytext)
library(ggplot2)##
## Attaching package: 'ggplot2'## The following object is masked from 'package:NLP':
##
## annotatelibrary(parallel)
library(tokenizers)
library(tau)
library(NLP)
library(stringr)
library(devtools)## Loading required package: usethislibrary(quanteda)## Package version: 3.3.1
## Unicode version: 13.0
## ICU version: 69.1## Parallel computing: 4 of 4 threads used.## See https://quanteda.io for tutorials and examples.##
## Attaching package: 'quanteda'## The following object is masked from 'package:tm':
##
## stopwords## The following objects are masked from 'package:NLP':
##
## meta, meta<-library(kayadata)
library(syuzhet)
library(e1071)
library(sentimentr)##
## Attaching package: 'sentimentr'## The following object is masked from 'package:syuzhet':
##
## get_sentenceslibrary(SentimentAnalysis)##
## Attaching package: 'SentimentAnalysis'## The following object is masked from 'package:base':
##
## writelibrary(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionlibrary(pacman)
pacman::p_load(textstem, dplyr)TENTANG DATASET
_Dataset yang digunakan adalah data yang diperoleh dari hasil crowling data di twitter. data ini berisi 100 lebih tweets tentang Prabowo atasi stunting
Import data ke dalam R untuk dilakukan analisis
setwd("C:/Users/kjl/Documents/Tugas Kuliah")
Prabowo.atasi.stunting <- read.csv("~/Tugas Kuliah/Prabowo-atasi-stunting.csv", sep=";")
tweets<-Prabowo.atasi.stunting$full_text
head(tweets)## [1] "@prabowo Bos BUMN, Erick Thohir, bakal seru nemenin Prabowo di Pilpres 2024! dekade08"
## [2] "@prabowo Erick Thohir, eks teknokrat BUMN, bisa jadi tandem oke buat Prabowo di Pilpres 2024! dekade08"
## [3] "@prabowo Selain relawan Pro Jokowi yang resmi mendeklarasikan dukungan untuk sang Ketua Umum Partai Gerindra itu, relawan Konco Prabowo Subianto juga menyampaikan hal senada. dekade08"
## [4] "@prabowo Selain relawan Pro Jokowi yang resmi mendeklarasikan dukungan untuk sang Ketua Umum Partai Gerindra itu, relawan Konco Prabowo juga menyampaikan hal senada. dekade08"
## [5] "@prabowo Erick Thohir, mantan Menteri BUMN, bisa jadi jagoan Prabowo Subianto di Pilpres 2024! dekade08"
## [6] "@prabowo Baliho bergambar Prabowo Subianto bersama Gibran Rakabuming Raka bertebaran di Banyumas, Jawa Tengah. dekade08"##duplikat
#duplicate
tweets <- skripsi%>%
as.data.frame() %>%
distinct()
tweets##jumlah baris tweet setelah duplikat dihapus
nrow(tweets)## NULL##hapus url
tweets <- tweets %>%
replace_html() %>%
replace_url()
tweets
tweets <- strip(tweets)
head(tweets)##stemming/lemmatizing = kata dasar
#stemming/lemmatizing = kata dasar
stem_strings(tweets)##cetak tweet dengan html yang dikonversi di index
replace_html(replace_emoji(tweets))melakukan tugas penggantian seluruh variabel teks
tweets <- tweets %>%
replace_emoji(.) %>%
replace_html(.)print menggantikan data teks pada indeks [4:5]
replace_tag(tweets)hapus mentions
tweets <- tweets %>%
replace_tag(tweets, pattern = "@([A-Za-z0-9_]+)",replacement="") %>% # remove mentions
replace_hash(tweets, pattern = "#([A-Za-z0-9_]+)",replacement="") # remove hashtags
tweets##strip simbol
tweets <- strip(tweets)##menghapus kata penghubung atau kata yang tidak baku
tweets <-removeWords(tweets, c("di","dan","yang","akan","agar","seperti","yaitu","kami","kami",
"mari","pada","jelang","dimana","dengan","sudah","ini","seluruh",
"diminta","tak","itu","hai","bisa","wib","oleh","mai","jam", "aug",
"masa","berikut","kalau","klik","ibodwq","terd","httpstconvv","tue","wed",
"httpstcoxu","yzmrlyx","tahapan","refaabdi","kota","kpu","kpuid","rt","hingga",
"saat", "belum","apa","sih","suara","pesta","dindap","http","httpstco",
"asn","bakal","wkwk","wkwkw","aug","iya","uu","i","ada","ngene","yang","bjir",
"ðÿðÿ","un","anjir","tahi","tbtb","my","wios","sialan","wkwkwkwk","sip","omo",
"like","plss","ket","e","after","ha","pakðÿ", "but","rill","cashback",
"allah","and","o","ðÿ'^ðÿ","nya","ya","ðÿ","no","nuruk","ki","jir",
"anjing","biar","kagak","sayang","mah","anjay","ngaruh","kalo","gua","thesis",
"skripsiðÿ","duh","ih","ots","a","pft","plis","plan","ra","rabi","o",
"skripshit","duit","sih","nih", "amp", "ï","tuh","tau","â","â","aaaa","deh","ðÿº",
"coba","dll","iki","gue","kena","oon","pas","sad","up","wkwkwk","waleh","ajg",
"ah","adaâ","alaala","alah","alamðÿ","allahâ","ayo","end","bu","biak","is"))
head(rev)##
## 1 function (x)
## 2 UseMethod("rev")lower case = mengubah huruf kapital menjadi huruf kecil
tweets <- tolower(tweets)
tweets##Mengembalikan Kata yang disingkat Menjadi Kata Aslinya
tweets <- replace_contraction(tweets)
tweets###Mengembalikan Kata yang Mengalami Perpanjangan Menjadi Kata Aslinya
tweets <- replace_word_elongation(tweets)
tweetsMenyimpang data yang sudah dibersihkan
write.csv(rev,file = "C:/Users/kjl/Documents/data-bersih3.csv", row.names = F) Mengubah Data Frame Menjadi Data Faktor
tdm <- TermDocumentMatrix(tweets)
m <- as.matrix(tdm)
v <- sort(rowSums(m),decreasing = TRUE)##Mengubah Data Faktor Menjadi Data Frame
d <- data.frame(word = names(v), freq = v)Membuast Diagram Worcloud
wordcloud(d$word, d$freq,
random.order = FALSE,
max.words = 500,
colors = brewer.pal(name="Dark2",8))
tdm <-TermDocumentMatrix (tweets,
control = list(wordLengths= c (1, inf)))
tdmperiksa kata-kata yang sering muncul
(freq.terms <- findFreqTerms(tdm, lowfreq = 14))## [1] "dekade" "pilpres" "prabowo" "jadi" "dukungan" "jokowi"
## [7] "partai" "resmi" "gibran" "projo" "fahri" "hamzah"term.freq <- rowSums(as.matrix(tdm))
term.freq <- subset(term.freq, term.freq >= 14)
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()
##Menghapus istilah-istilah yang jarang?
tdm2 <- removeSparseTerms(tdm, sparse = 0.95)
m2 <- as.matrix(tdm2)ANALISIS CLUSTER HIERARKI
distMatrix <- dist(scale (m2))
fit <- hclust (distMatrix, method = "ward")## The "ward" method has been renamed to "ward.D"; note new "ward.D2"plot(fit)
rect.hclust(fit, k = 4)
ANALISIS CLUSTER K-MEANS
m3 <- t(m2) # transpose the matrix to cluster documents (tweets)
m3## Terms
## Docs dekade erick pilpres prabowo thohir buat jadi tandem dukungan gerindra
## 1 1 1 1 2 1 0 0 0 0 0
## 2 1 1 1 2 1 1 1 1 0 0
## 3 1 0 0 2 0 0 0 0 1 1
## 4 1 0 0 2 0 0 0 0 1 1
## 5 1 1 1 2 1 0 1 0 0 0
## 6 1 0 0 2 0 0 0 0 0 0
## 7 1 0 0 2 0 0 0 0 1 0
## 8 1 1 0 2 1 0 0 0 0 0
## 9 1 1 1 2 1 1 0 1 0 0
## 10 1 1 0 2 1 0 0 0 0 0
## 11 1 0 1 2 0 0 0 0 0 0
## 12 1 0 1 2 0 0 0 0 0 0
## 13 0 0 0 0 0 0 0 0 0 0
## 14 1 0 0 2 0 0 0 0 0 0
## 15 1 0 1 2 0 0 0 0 0 0
## 16 1 0 1 2 0 1 0 0 0 0
## 17 1 0 0 2 0 0 0 0 1 0
## 18 1 0 0 2 0 0 0 0 0 0
## 19 1 0 1 2 0 0 1 0 0 0
## 20 1 0 0 2 0 0 0 0 0 0
## 21 1 0 1 3 0 0 0 0 0 0
## 22 1 0 0 2 0 0 0 0 0 1
## 23 1 0 0 2 0 1 1 0 0 0
## 24 1 0 0 2 0 0 0 0 0 0
## 25 1 0 0 2 0 0 0 0 0 0
## 26 1 0 0 2 0 0 0 0 1 0
## 27 1 0 0 3 0 0 0 0 0 0
## 28 1 0 0 3 0 0 0 0 0 0
## 29 1 0 0 2 0 0 0 0 0 0
## 30 1 0 0 2 0 0 0 0 1 0
## 31 1 0 1 2 0 0 0 0 0 0
## 32 1 0 0 2 0 0 0 0 1 0
## 33 1 0 0 2 0 0 0 0 0 0
## 34 1 0 0 2 0 0 0 0 0 0
## 35 1 0 0 2 0 0 0 0 0 0
## 36 1 0 1 2 0 0 0 0 0 0
## 37 1 0 0 2 0 0 0 0 0 1
## 38 1 0 1 2 0 1 0 0 0 0
## 39 1 0 0 3 0 0 0 0 0 0
## 40 1 0 0 2 0 0 0 0 0 0
## 41 1 0 0 2 0 0 0 0 0 0
## 42 1 0 0 1 0 0 0 0 0 0
## 43 1 0 0 2 0 0 0 0 1 0
## 44 1 0 1 2 0 0 1 1 0 0
## 45 1 0 0 2 0 0 0 0 0 0
## 46 1 0 0 2 0 0 0 0 0 0
## 47 1 0 1 2 0 0 0 0 0 0
## 48 1 0 0 2 0 0 1 0 0 0
## 49 1 0 0 2 0 0 0 0 0 0
## 50 1 0 0 2 0 0 0 0 0 0
## 51 1 0 0 2 0 0 0 0 0 0
## 52 1 0 0 2 0 0 0 0 0 0
## 53 1 1 1 2 1 0 1 0 0 0
## 54 1 0 0 2 0 0 1 0 0 0
## 55 1 1 1 2 1 1 0 1 0 0
## 56 1 0 0 2 0 0 0 0 0 0
## 57 1 0 0 2 0 0 0 0 0 0
## 58 1 0 0 2 0 0 0 0 0 0
## 59 1 0 1 3 0 0 0 0 1 0
## 60 1 0 0 3 0 0 0 0 1 0
## 61 1 0 0 2 0 0 0 0 0 1
## 62 1 0 0 2 0 0 0 0 0 1
## 63 1 0 1 2 0 0 1 0 0 0
## 64 1 0 0 2 0 0 0 0 0 0
## 65 1 0 0 2 0 0 0 0 0 0
## 66 1 0 1 1 0 0 0 1 0 0
## 67 1 0 0 2 0 0 1 0 0 1
## 68 1 0 0 2 0 0 0 0 0 1
## 69 1 0 1 1 0 0 0 1 0 0
## 70 1 0 0 2 0 0 0 0 0 0
## 71 1 0 0 2 0 0 0 0 0 0
## 72 1 0 1 2 0 0 0 0 0 0
## 73 1 0 0 1 0 0 0 0 0 0
## 74 1 0 0 2 0 0 0 0 1 0
## 75 1 0 0 2 0 0 0 0 0 0
## 76 1 0 0 2 0 0 0 0 0 0
## 77 1 0 0 2 0 1 1 0 0 0
## 78 1 0 0 2 0 0 0 0 0 0
## 79 1 0 0 2 0 1 1 0 0 0
## 80 1 0 0 1 0 0 1 0 1 0
## 81 1 0 0 2 0 0 0 0 0 0
## 82 1 0 0 2 0 0 0 0 0 0
## 83 1 0 0 3 0 0 0 0 0 0
## 84 1 0 1 2 0 0 0 0 0 0
## 85 1 0 1 2 0 1 0 0 0 0
## 86 1 0 0 2 0 0 0 0 1 0
## 87 1 0 1 2 0 0 0 0 0 0
## 88 1 0 1 2 0 0 0 0 0 0
## 89 1 0 1 3 0 0 0 0 0 0
## 90 1 0 0 2 0 0 0 0 0 0
## 91 1 0 1 3 0 1 0 0 1 0
## 92 1 0 1 2 0 0 0 0 0 0
## 93 1 0 0 2 0 0 1 0 0 0
## 94 1 0 1 2 0 0 1 1 0 0
## 95 1 0 0 2 0 0 0 0 0 0
## 96 1 0 0 2 0 0 1 0 0 0
## 97 1 0 1 2 0 0 0 0 0 0
## 98 1 0 0 2 0 0 0 0 0 0
## 99 1 0 1 3 0 0 0 0 0 0
## 100 1 0 0 2 0 0 0 0 1 0
## 101 1 0 0 2 0 0 0 0 1 0
## Terms
## Docs jokowi juga partai relawan resmi subianto untuk gibran rakabuming
## 1 0 0 0 0 0 0 0 0 0
## 2 0 0 0 0 0 0 0 0 0
## 3 1 1 1 2 1 1 1 0 0
## 4 1 1 1 2 1 0 1 0 0
## 5 0 0 0 0 0 1 0 0 0
## 6 0 0 0 0 0 1 0 1 1
## 7 1 0 0 0 0 0 0 0 0
## 8 0 0 0 0 0 1 0 0 0
## 9 0 0 0 0 0 0 0 0 0
## 10 0 0 0 0 0 0 0 0 0
## 11 0 1 0 0 0 0 0 0 0
## 12 0 0 1 0 0 1 0 0 0
## 13 0 0 0 0 0 0 0 0 0
## 14 0 0 0 0 0 0 0 1 0
## 15 0 0 1 0 0 0 0 0 0
## 16 0 0 0 0 0 0 0 1 0
## 17 1 0 0 0 0 0 0 0 0
## 18 1 0 0 0 1 0 1 0 0
## 19 0 0 0 0 0 1 0 1 0
## 20 1 0 0 0 0 0 0 0 0
## 21 1 0 0 0 1 0 1 0 0
## 22 0 0 0 0 0 0 0 0 0
## 23 0 0 1 0 0 0 0 0 0
## 24 0 1 0 0 0 0 0 0 0
## 25 1 0 0 0 0 0 0 0 0
## 26 1 0 0 0 0 0 0 0 0
## 27 1 0 0 0 0 0 0 0 0
## 28 1 0 0 0 0 0 0 0 0
## 29 1 0 0 0 0 0 0 0 0
## 30 1 0 0 0 0 0 0 0 0
## 31 0 0 0 0 0 0 0 0 0
## 32 1 0 0 0 0 0 1 0 0
## 33 0 1 0 0 0 1 0 0 0
## 34 0 0 1 0 0 0 0 0 0
## 35 0 0 2 0 0 0 0 0 0
## 36 0 0 0 0 0 0 0 0 0
## 37 0 0 0 0 0 0 0 0 0
## 38 0 0 0 0 0 0 0 1 0
## 39 1 0 0 0 1 0 0 0 0
## 40 1 0 0 0 1 0 1 0 0
## 41 0 0 0 0 0 0 0 0 0
## 42 0 0 0 0 0 0 0 1 1
## 43 0 0 0 1 0 0 0 0 0
## 44 0 0 0 0 0 1 0 1 1
## 45 0 0 1 0 0 0 0 0 0
## 46 0 0 0 0 0 0 0 0 0
## 47 0 0 0 0 0 0 0 0 0
## 48 0 0 0 0 0 0 0 0 0
## 49 0 0 1 0 0 0 0 0 0
## 50 1 0 0 0 0 1 0 0 0
## 51 0 0 0 0 0 0 0 0 0
## 52 0 0 0 0 1 0 0 0 0
## 53 0 1 0 0 0 1 0 0 0
## 54 0 0 0 0 0 0 0 1 0
## 55 0 0 0 0 0 0 0 0 0
## 56 0 0 0 0 1 0 0 0 0
## 57 0 0 0 1 0 0 0 0 0
## 58 0 0 0 0 0 0 0 1 0
## 59 1 0 0 0 1 0 1 0 0
## 60 1 0 0 0 0 0 0 0 0
## 61 0 0 2 0 0 1 0 0 0
## 62 0 0 0 0 0 0 0 0 0
## 63 0 0 0 0 0 0 0 1 0
## 64 0 0 1 0 0 0 0 0 0
## 65 1 0 0 0 0 0 0 0 0
## 66 0 0 0 0 0 0 0 0 0
## 67 0 0 0 0 0 0 0 0 0
## 68 0 0 0 0 1 0 0 0 0
## 69 0 0 0 0 0 0 0 0 0
## 70 0 0 1 0 0 0 0 0 0
## 71 1 0 0 0 0 0 0 0 0
## 72 0 0 0 0 0 0 0 0 0
## 73 0 0 0 0 0 0 0 1 1
## 74 1 0 0 0 0 0 0 0 0
## 75 0 0 1 0 0 0 0 0 0
## 76 0 0 0 0 1 0 0 0 0
## 77 0 0 0 0 0 0 0 1 0
## 78 0 0 1 0 0 0 0 0 0
## 79 0 0 0 0 0 0 0 1 0
## 80 0 0 0 0 0 0 1 1 0
## 81 0 0 1 0 0 0 0 0 0
## 82 0 0 0 1 0 1 0 0 0
## 83 1 0 0 0 0 0 0 0 0
## 84 0 0 0 0 0 0 0 0 0
## 85 0 0 0 0 0 0 0 1 1
## 86 1 0 0 0 0 0 0 0 0
## 87 0 0 0 0 0 0 0 0 0
## 88 0 0 0 0 0 0 0 0 0
## 89 1 0 0 0 1 0 0 0 0
## 90 0 0 1 0 0 0 0 0 0
## 91 0 0 0 0 1 0 0 0 0
## 92 0 0 0 0 0 0 0 0 0
## 93 0 0 0 0 0 0 0 0 0
## 94 0 0 0 0 0 0 0 1 1
## 95 0 0 0 0 0 0 0 1 0
## 96 0 0 0 0 0 0 0 1 0
## 97 0 0 0 1 0 0 0 0 0
## 98 1 0 0 0 0 0 0 0 0
## 99 1 0 0 0 1 0 1 0 0
## 100 1 0 0 0 0 0 1 0 0
## 101 0 0 0 1 0 1 0 0 0
## Terms
## Docs melanjutkan programprogram projo menang golkar pan fahri hamzah program
## 1 0 0 0 0 0 0 0 0 0
## 2 0 0 0 0 0 0 0 0 0
## 3 0 0 0 0 0 0 0 0 0
## 4 0 0 0 0 0 0 0 0 0
## 5 0 0 0 0 0 0 0 0 0
## 6 0 0 0 0 0 0 0 0 0
## 7 1 1 1 0 0 0 0 0 0
## 8 0 0 0 0 0 0 0 0 0
## 9 0 0 0 0 0 0 0 0 0
## 10 0 0 0 0 0 0 0 0 0
## 11 0 0 0 1 0 0 0 0 0
## 12 0 0 0 0 1 1 0 0 0
## 13 0 0 0 0 0 0 0 0 0
## 14 0 0 0 0 0 0 1 1 0
## 15 0 0 0 0 1 1 0 0 0
## 16 0 0 0 0 0 0 1 1 0
## 17 0 0 1 0 0 0 0 0 1
## 18 1 0 1 0 0 0 0 0 1
## 19 0 0 0 0 0 0 1 1 0
## 20 0 1 0 0 0 0 0 0 0
## 21 0 0 1 0 0 0 0 0 1
## 22 0 0 0 0 1 1 0 0 0
## 23 0 0 0 0 0 0 0 0 0
## 24 0 0 0 0 0 0 0 0 0
## 25 0 1 1 0 0 0 0 0 0
## 26 1 1 1 0 0 0 0 0 0
## 27 1 1 1 0 0 0 0 0 0
## 28 0 0 1 0 0 0 0 0 1
## 29 1 0 0 0 0 0 0 0 0
## 30 0 0 1 0 0 0 0 0 1
## 31 0 0 0 0 0 0 1 1 0
## 32 1 0 1 0 0 0 0 0 0
## 33 0 0 0 0 0 0 0 0 0
## 34 0 0 1 0 0 0 0 0 0
## 35 0 0 0 0 0 0 1 1 0
## 36 0 0 1 1 0 0 0 0 0
## 37 0 0 0 0 1 1 0 0 0
## 38 0 0 0 0 0 0 1 1 0
## 39 1 1 1 0 0 0 0 0 0
## 40 1 0 1 0 0 0 0 0 1
## 41 0 0 1 0 0 0 0 0 0
## 42 0 0 0 0 0 0 1 1 0
## 43 0 0 0 0 0 0 0 0 0
## 44 0 0 0 0 0 0 1 1 0
## 45 0 0 1 0 0 0 0 0 0
## 46 0 0 1 1 0 0 0 0 0
## 47 0 0 0 0 0 0 1 1 0
## 48 0 0 1 0 0 0 0 0 0
## 49 0 0 0 0 0 0 0 0 0
## 50 0 0 0 0 0 0 0 0 1
## 51 0 0 1 0 0 0 0 0 0
## 52 0 0 1 0 0 0 0 0 0
## 53 0 0 0 0 0 0 0 0 0
## 54 0 0 0 0 0 0 0 0 0
## 55 0 0 0 0 0 0 0 0 0
## 56 0 0 1 0 0 0 0 0 0
## 57 0 0 0 0 0 0 0 0 0
## 58 0 0 0 0 0 0 0 0 0
## 59 0 0 1 0 0 0 0 0 1
## 60 0 1 1 0 0 0 0 0 0
## 61 0 0 0 0 0 0 0 0 0
## 62 0 0 0 0 1 1 0 0 0
## 63 0 0 0 0 0 0 1 1 0
## 64 0 0 1 0 0 0 0 0 0
## 65 0 0 0 1 0 0 0 0 1
## 66 0 0 0 0 0 0 1 1 0
## 67 0 0 0 0 1 1 0 0 0
## 68 0 0 0 0 1 1 0 0 0
## 69 0 0 0 0 0 0 1 1 0
## 70 0 0 1 0 0 0 0 0 0
## 71 0 1 0 0 0 0 0 0 0
## 72 0 0 0 0 0 0 1 1 0
## 73 0 0 0 0 0 0 1 1 0
## 74 0 0 1 0 0 0 0 0 0
## 75 0 0 1 0 0 0 0 0 0
## 76 0 0 1 0 0 0 0 0 0
## 77 0 0 0 0 0 0 0 0 0
## 78 0 0 1 0 0 0 0 0 0
## 79 0 0 0 0 0 0 1 1 0
## 80 0 0 0 0 0 0 0 0 0
## 81 0 0 1 0 0 0 0 0 0
## 82 0 0 0 1 0 0 0 0 0
## 83 0 0 1 0 0 0 0 0 1
## 84 0 0 0 0 0 0 1 1 0
## 85 0 0 0 0 0 0 1 1 0
## 86 0 0 1 0 0 0 0 0 0
## 87 0 0 1 1 0 0 0 0 0
## 88 0 0 1 1 0 0 0 0 0
## 89 0 0 1 0 0 0 0 0 1
## 90 0 0 1 0 0 0 0 0 0
## 91 0 0 1 0 0 0 0 0 0
## 92 0 0 1 1 0 0 0 0 0
## 93 0 0 1 0 0 0 0 0 0
## 94 0 0 0 0 0 0 1 1 0
## 95 0 0 0 0 0 0 0 0 0
## 96 0 0 0 0 0 0 0 0 0
## 97 0 0 1 1 0 0 0 0 0
## 98 0 0 0 0 0 0 0 0 0
## 99 0 0 1 0 0 0 0 0 1
## 100 1 0 1 0 0 0 0 0 0
## 101 0 0 0 0 0 0 0 0 0
## Terms
## Docs calon gelora presiden sebagai cawapres feb rakyat satu dukung
## 1 0 0 0 0 0 0 0 0 0
## 2 0 0 0 0 0 0 0 0 0
## 3 0 0 0 0 0 0 0 0 0
## 4 0 0 0 0 0 0 0 0 0
## 5 0 0 0 0 0 0 0 0 0
## 6 0 0 0 0 0 0 0 0 0
## 7 0 0 0 0 0 0 0 0 0
## 8 0 0 0 0 0 0 0 0 0
## 9 0 0 0 0 0 0 0 0 0
## 10 0 0 0 0 0 0 0 0 0
## 11 0 0 0 0 0 0 0 0 0
## 12 0 0 0 0 0 0 0 0 0
## 13 0 0 0 0 0 0 0 0 0
## 14 0 0 0 0 0 0 0 0 0
## 15 0 0 0 0 0 0 0 0 0
## 16 0 0 0 0 0 0 0 0 0
## 17 0 0 0 0 0 0 0 0 0
## 18 0 0 0 0 0 0 0 0 0
## 19 1 0 0 0 0 0 0 0 0
## 20 0 0 0 0 0 0 0 0 0
## 21 0 0 0 0 0 0 0 0 0
## 22 0 1 0 0 0 0 0 0 0
## 23 0 0 0 0 0 0 0 0 0
## 24 0 0 1 1 0 0 0 0 0
## 25 0 0 0 0 0 0 0 0 0
## 26 0 0 0 0 0 0 0 0 0
## 27 0 0 0 0 0 0 0 0 0
## 28 1 0 1 1 0 0 0 0 0
## 29 0 0 0 0 0 0 0 0 0
## 30 0 0 0 0 0 0 0 0 0
## 31 0 0 0 0 1 0 0 0 0
## 32 0 0 0 0 0 0 0 0 0
## 33 0 0 1 1 0 0 0 0 0
## 34 0 0 0 0 0 1 1 0 0
## 35 0 2 0 0 0 0 0 0 0
## 36 0 0 0 0 0 0 0 1 0
## 37 0 1 0 0 0 0 0 0 0
## 38 0 0 0 0 0 0 0 0 0
## 39 0 0 0 0 0 0 0 0 0
## 40 0 0 0 0 0 0 0 0 0
## 41 0 0 0 1 0 0 0 0 0
## 42 0 0 0 0 0 0 0 0 0
## 43 1 0 1 0 0 0 0 1 0
## 44 0 0 0 0 0 0 0 0 0
## 45 0 0 1 0 0 1 2 0 0
## 46 0 0 0 0 0 0 0 1 0
## 47 0 0 0 0 1 0 0 0 0
## 48 0 0 0 0 0 0 0 0 0
## 49 0 0 0 0 0 0 0 0 0
## 50 0 0 0 0 0 0 0 0 0
## 51 0 0 0 0 0 0 0 0 0
## 52 0 0 0 0 0 0 0 0 1
## 53 0 0 0 0 0 0 0 0 0
## 54 0 0 0 0 1 0 0 0 0
## 55 0 0 0 0 0 0 0 0 0
## 56 0 0 0 0 0 0 0 0 0
## 57 0 0 0 0 0 0 0 0 0
## 58 0 0 0 0 0 0 0 0 0
## 59 0 0 0 0 0 0 0 0 0
## 60 0 0 0 0 0 0 0 0 0
## 61 0 0 0 0 0 0 0 0 0
## 62 0 1 0 1 0 0 0 0 0
## 63 1 0 0 0 0 0 0 0 0
## 64 0 0 0 0 0 1 1 0 0
## 65 0 0 0 0 0 0 0 0 0
## 66 0 0 0 0 0 0 0 0 0
## 67 0 1 0 0 0 0 0 0 0
## 68 0 1 0 0 0 0 0 0 0
## 69 0 0 0 0 0 0 0 0 0
## 70 0 0 1 0 0 1 1 0 0
## 71 0 0 1 0 0 0 0 0 0
## 72 0 0 0 0 1 0 0 0 0
## 73 0 0 0 0 0 0 0 0 0
## 74 0 0 0 0 0 0 0 0 0
## 75 0 0 1 0 0 1 1 0 0
## 76 0 0 0 0 0 0 0 0 0
## 77 0 0 0 0 1 0 0 0 0
## 78 0 0 1 0 0 1 1 0 0
## 79 0 0 0 0 0 0 0 0 0
## 80 0 0 0 0 1 0 0 0 0
## 81 0 0 0 0 0 1 1 0 0
## 82 0 0 0 0 0 0 0 0 0
## 83 1 0 1 1 0 0 0 0 0
## 84 0 0 0 0 1 0 0 0 0
## 85 0 0 0 0 0 0 0 0 0
## 86 0 0 0 0 0 0 0 0 0
## 87 0 0 0 0 0 0 0 1 1
## 88 0 0 0 0 0 0 0 1 0
## 89 0 0 0 0 0 0 0 0 1
## 90 0 0 0 0 0 1 1 0 0
## 91 0 0 0 0 0 0 0 0 1
## 92 0 0 0 0 0 0 0 1 1
## 93 0 0 0 0 0 0 0 0 0
## 94 0 0 0 0 0 0 0 0 0
## 95 0 0 0 0 1 0 0 0 1
## 96 0 0 0 0 1 0 0 0 0
## 97 0 0 0 0 0 0 0 0 0
## 98 0 0 0 0 0 0 1 0 0
## 99 0 0 0 0 0 0 0 0 0
## 100 0 0 0 0 0 0 0 0 0
## 101 1 0 1 0 0 0 0 1 0set.seed(122)
k<- 3
kmeansResult<-kmeans(m3, k)
round(kmeansResult$centers, digits=3)## dekade erick pilpres prabowo thohir buat jadi tandem dukungan gerindra
## 1 0.983 0.133 0.233 1.950 0.133 0.083 0.183 0.050 0.050 0.100
## 2 1.000 0.000 0.217 2.435 0.000 0.043 0.000 0.000 0.565 0.087
## 3 1.000 0.000 0.722 1.778 0.000 0.222 0.278 0.222 0.000 0.000
## jokowi juga partai relawan resmi subianto untuk gibran rakabuming
## 1 0.100 0.067 0.233 0.083 0.067 0.167 0.017 0.117 0.017
## 2 0.957 0.087 0.087 0.174 0.435 0.043 0.391 0.000 0.000
## 3 0.000 0.000 0.111 0.000 0.000 0.111 0.000 0.611 0.278
## melanjutkan programprogram projo menang golkar pan fahri hamzah program
## 1 0.017 0.033 0.350 0.15 0.117 0.117 0 0 0.033
## 2 0.348 0.261 0.913 0.00 0.000 0.000 0 0 0.435
## 3 0.000 0.000 0.000 0.00 0.000 0.000 1 1 0.000
## calon gelora presiden sebagai cawapres feb rakyat satu dukung
## 1 0.033 0.083 0.150 0.067 0.083 0.133 0.167 0.117 0.067
## 2 0.087 0.000 0.087 0.087 0.000 0.000 0.000 0.000 0.087
## 3 0.111 0.111 0.000 0.000 0.222 0.000 0.000 0.000 0.000for (i in 1:k) {
cat(paste("cluster ", i, ": ", sep = ""))
s <- sort(kmeansResult$centers[i, ], decreasing = T)
cat(names(s)[1:5], "\n")
# print the tweets of every cluster
# print(tweets[which(kmeansResult£cluster==i)])
}## cluster 1: prabowo dekade projo pilpres partai
## cluster 2: prabowo dekade jokowi projo dukungan
## cluster 3: prabowo dekade fahri hamzah pilpres