ANALISIS DATA TWEET TIMNAS
ST NURAVIAT AWAINA
2023-12-11
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)## Warning in stringi::stri_info(): Your current locale is not in the list of
## available locales. Some functions may not work properly. Refer to
## stri_locale_list() for more details on known locale specifiers.
## Warning in stringi::stri_info(): Your current locale is not in the list of
## available locales. Some functions may not work properly. Refer to
## stri_locale_list() for more details on known locale specifiers.## 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_gh("trinker/textstem")
pacman::p_load(textstem, dplyr)#input data
setwd("C:/Users/LENOVO/Documents/UTS_ST NURAVIAT AWAINA_E0221003")
DATATIMNAS<-read.csv("~/UTS_ST NURAVIAT AWAINA_E0221003/timnas.csv", sep=";")
rev <- DATATIMNAS$full_text
head(rev)## [1] "Looks like African playing for indonesia, should have played all 11 African players"
## [2] "Hugo Samir Bin Jackson F Tiago 💪ðŸ\u008f¿"
## [3] "Masuk ngegolim, Hugo samir✌"
## [4] "golnya keren & tidak disangka sangka ðŸ‘\u008d🤣"
## [5] "alhamdulillah menang"
## [6] "Mantap Garuda muda."lower case = mengubah huruf kapital menjadi huruf kecil
rev <- tolower(rev)
head(rev)## [1] "looks like african playing for indonesia, should have played all 11 african players"
## [2] "hugo samir bin jackson f tiago ðÿ’ªðÿ\u008f¿"
## [3] "masuk ngegolim, hugo samir✜"
## [4] "golnya keren & tidak disangka sangka ðÿ‘\u008dðÿ¤£"
## [5] "alhamdulillah menang"
## [6] "mantap garuda muda."#Mengembalikan Kata yang disingkat Menjadi Kata Aslinya
rev <- replace_contraction(rev)
head(rev)## [1] "looks like african playing for indonesia, should have played all 11 african players"
## [2] "hugo samir bin jackson f tiago ðÿ’ªðÿ\u008f¿"
## [3] "masuk ngegolim, hugo samir✜"
## [4] "golnya keren & tidak disangka sangka ðÿ‘\u008dðÿ¤£"
## [5] "alhamdulillah menang"
## [6] "mantap garuda muda."#Mengembalikan Kata yang Mengalami Perpanjangan Menjadi Kata Aslinya
rev <- replace_word_elongation(rev)
head(rev)## [1] "looks like african playing for indonesia, should have played all 11 african players"
## [2] "hugo samir bin jackson f tiago ðÿ’ªðÿ\u008f¿"
## [3] "masuk ngegolim, hugo samir✜"
## [4] "golnya keren & tidak disangka sangka ðÿ‘\u008dðÿ¤£"
## [5] "alhamdulillah menang"
## [6] "mantap garuda muda."#Menghapus simbol
rev <- strip(rev)
head(rev)## [1] "looks like african playing for indonesia should have played all african players"
## [2] "hugo samir bin jackson f tiago ðÿªðÿ\u008f"
## [3] "masuk ngegolim hugo samir✜"
## [4] "golnya keren amp tidak disangka sangka ðÿ\u008dðÿ"
## [5] "alhamdulillah menang"
## [6] "mantap garuda muda"#stemming/lemmatizing = kata dasar
rev<-stem_strings(rev)
head(rev)## [1] "look like african plai for indonesia should have plai all african player"
## [2] "hugo samir bin jackson f tiago ðÿªðÿ\u008f"
## [3] "masuk ngegolim hugo samir✜"
## [4] "golnya keren amp tidak disangka sangka ðÿ\u008dðÿ"
## [5] "alhamdulillah menang"
## [6] "mantap garuda muda"rev<-lemmatize_strings(rev)
head(rev)## [1] "look like african plai for indonesia should have plai all african player"
## [2] "hugo samir bin jackson f tiago ðÿªðÿ\u008f"
## [3] "masuk ngegolim hugo samir✜"
## [4] "golnya keren amp tidak disangka sangka ðÿ\u008dðÿ"
## [5] "alhamdulillah menang"
## [6] "mantap garuda muda"sc<-c("driver","drive","drove","driven","drives","driving")
sc## [1] "driver" "drive" "drove" "driven" "drives" "driving"stem_words(sc)## [1] "driver" "drive" "drove" "driven" "drive" "drive"lemmatize_words(sc)## [1] "driver" "drive" "drive" "drive" "drive" "drive"#menghapus kata penghubung
rev <-removeWords(rev, 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",
"masa","berikut","kalau","klik","ibodwq","terd","httpstconvv",
"httpstcoxu","yzmrlyx","tahapan","refaabdi","kota","kpu","kpuid","rt","hingga","saat",
"belum","apa","sih","suara","pesta","dindap","http","httpstco","asn","bakal"))
head(rev)## [1] "look like african plai for indonesia should have plai all african player"
## [2] "hugo samir bin jackson f tiago ðÿªðÿ\u008f"
## [3] "masuk ngegolim hugo samir✜"
## [4] "golnya keren amp tidak disangka sangka ðÿ\u008dðÿ"
## [5] "alhamdulillah menang"
## [6] "mantap garuda muda"write.csv(rev,file = "C:/Users/LENOVO/Documents/UTS_ST NURAVIAT AWAINA_E0221003/databersihTIMNAS.csv", row.names = F) ##Membuat Word Cloud #Mengubah Data Frame Menjadi Data Faktor
tdm <- TermDocumentMatrix(rev)
tdm## <<TermDocumentMatrix (terms: 491, documents: 113)>>
## Non-/sparse entries: 719/54764
## Sparsity : 99%
## Maximal term length: 24
## Weighting : term frequency (tf)m <- as.matrix(tdm)
View(m)
v <- sort(rowSums(m),decreasing = TRUE)
head(v)## hugo keren timna samir indonesia garuda
## 13 9 9 8 7 7#Mengubah Data Faktor Menjadi Data Frame
d <- data.frame(word = names(v), freq = v)
head(d)## word freq
## hugo hugo 13
## keren keren 9
## timna timna 9
## samir samir 8
## indonesia indonesia 7
## garuda garuda 7wordcloud(d$word, d$freq,
random.order = FALSE,
max.words = 500,
colors = brewer.pal(name = "Dark2",8 )) 
##Term Dokument Matriks
tdm <- TermDocumentMatrix(rev,
control = list(wordLengths = c(1, Inf)))
tdm## <<TermDocumentMatrix (terms: 515, documents: 113)>>
## Non-/sparse entries: 759/57436
## Sparsity : 99%
## Maximal term length: 24
## Weighting : term frequency (tf)inspect frequent words
(freq.terms <- findFreqTerms(tdm, lowfreq = 5))## [1] "indonesia" "hugo" "samir" "keren" "menang" "garuda"
## [7] "mantap" "timna" "pemain" "banget" "gak" "gol"
## [13] "witan" "mainnya" "yg" "ga" "jadi" "ada"term.freq <- rowSums(as.matrix(tdm))
term.freq <- subset(term.freq, term.freq >= 5)
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()
# which words are associated with ‘r’?
findAssocs(tdm, "indonesia", 0.25)## $indonesia
## african for have like look
## 0.37 0.37 0.37 0.37 0.37
## plai player should bawa hiclqtsd
## 0.37 0.37 0.37 0.37 0.37
## httpstcoz ramai u adalah kelebihan
## 0.37 0.37 0.37 0.37 0.37
## ku victor gara kalah alquran
## 0.37 0.37 0.37 0.37 0.37
## httpstcoegdqw kbd lho mantep nyangka
## 0.37 0.37 0.37 0.37 0.37
## penghaf sepakbola si wonderkid yaa
## 0.37 0.37 0.37 0.37 0.37
## samir hugo
## 0.36 0.25findAssocs(tdm, "gol", 0.2)## $gol
## gak kalo bener biasakan dapat dulugak enakeun
## 0.47 0.45 0.40 0.40 0.40 0.40 0.40
## ginidapat gitu ivar jener kayak modelan nah
## 0.40 0.40 0.40 0.40 0.40 0.40 0.40
## nekuk nihayo set sit teh umpanbawa usah
## 0.40 0.40 0.40 0.40 0.40 0.40 0.40
## bobol dibawah eh kirgistan kl ngak pelatihnya
## 0.40 0.40 0.40 0.40 0.40 0.40 0.40
## sepadan skillnya tahunya takut tuh uzbekistan pertamanya
## 0.40 0.40 0.40 0.40 0.40 0.40 0.40
## mah dluan udah witan babak punya gocek
## 0.40 0.40 0.31 0.30 0.27 0.27 0.27
## perlu sbelum selebrasi dulu sama
## 0.27 0.27 0.27 0.21 0.21remove sparse terms
tdm2 <- removeSparseTerms(tdm, sparse = 0.95)
m2 <- as.matrix(tdm2)cluster hierarchical terms
distMatrix <- dist(scale(m2))
fit <- hclust(distMatrix, method = "ward")## The "ward" method has been renamed to "ward.D"; note new "ward.D2"fit##
## Call:
## hclust(d = distMatrix, method = "ward")
##
## Cluster method : ward.D
## Distance : euclidean
## Number of objects: 10plot(fit)
rect.hclust(fit, k = 2)
# cut tree into 5 clusters #Cluster k-means
m3 <- t(m2)transpose the matrix to cluster documents (tweets)
set.seed(122)set a fixed random seed
k <- 5 number of clusters
kmeansResult <- kmeans(m3, k)
round(kmeansResult$centers, digits = 3) # cluster centers## indonesia hugo samir keren garuda timna banget gak gol witan
## 1 0.000 0 0 0.000 0.00 1.333 0.000 0.333 0.333 0
## 2 0.000 0 0 0.000 0.00 0.000 0.000 0.333 0.333 1
## 3 0.375 1 1 0.000 0.00 0.125 0.000 0.125 0.000 0
## 4 0.045 0 0 0.102 0.08 0.000 0.068 0.011 0.023 0
## 5 0.000 1 0 0.000 0.00 0.000 0.000 0.000 0.000 0for (i in 1:k) {
cat(paste("cluster ", i, ": ", sep = ""))
s <- sort(kmeansResult$centers[i, ], decreasing = T)
cat(names(s)[1:5], "\n")
# print the tweets of every cluster
# print(tweets[which(kmeansResult£cluster==i)])
}## cluster 1: timna gak gol indonesia hugo
## cluster 2: witan gak gol indonesia hugo
## cluster 3: hugo samir indonesia timna gak
## cluster 4: keren garuda banget indonesia gol
## cluster 5: hugo indonesia samir keren garuda##Analisis Sentiment # import data dari excel (.csv)
databersih <- read.csv("~/UTS_ST NURAVIAT AWAINA_E0221003/databersih.csv", sep=";")
View(databersih)Buat DataFrame hanya untuk komentar positive
komentar_positif <- databersih %>%
filter(komen == "positive")
komentar_positif <-komentar_positif$x
komentar_positif## [1] "looks like african playing for indonesia should have played all african players"
## [2] "hugo samir bin jackson f tiago ðÿªðÿ\u008f"
## [3] "masuk ngegolim hugo samir✜"
## [4] "golnya keren amp tidak disangka sangka ðÿ\u008dðÿ"
## [5] "alhamdulillah menang"
## [6] "mantap garuda muda"
## [7] "garuda bangkit lagii"
## [8] "yukk garuda "
## [9] "mantap garuda muda menang laga perdana asian games ðÿ\u008dðÿðÿ httpstcoaaryso ipz"
## [10] "cakep speed kencengðÿœ"
## [11] "ramai rumakiek hugo samir bawa timnas indonesia u menang httpstcoz hiclqtsd"
## [12] "kelebihan para pemain indonesia adalah speed kenceng"
## [13] "jackson f thiago pasti bahagia"
## [14] "coach jacksen f tiago tersenyum simpul httpstcoadveosdcq"
## [15] "gila larinye cepet banget"
## [16] "pemain potensial cuma dia sering emosian tinggal atasi terus berkembang"
## [17] " kalo witan gak gol"
## [18] "sempet dag dig dug pesimis liat mainnya babak pertama monoton bgt tpi alhamdulillah berprogres dibabak keduagas truss garuda"
## [19] "laju banget akselerasinya"
## [20] "good timnas ðÿðÿðÿðÿ\u008f good coach indra sjahfri biasa nya mreka klau timnas menang sty yg banggakan sampai muji gak ktulunganðÿ giliran coach lokal mreka mengakui para pmain timnas ah mata sty anðÿ"
## [21] "punya prospek bagus dimasa depan asal jangan cepat puas banyak berlatih jaga emosi ingat dia pernah divonis tahun gak boleh main bola garagara emosian menendang wasit"
## [22] "hafidz quran nih anak keren respect"
## [23] "pemain mana hugo samir"
## [24] "hugo samir is supersub âšðÿðÿðÿðÿ"
## [25] " kejayaan sepak bola indonesiasegera dimulai waktunya bersatu do' viking jakarta"
## [26] "the next osimhen"
## [27] "nah bener kayak ginidapat umpanbawa sat set sat set gol gak usah nekuk dulugak perlu gocek dulu modelan ivar jener nihayo pemain timnas biasakan kayak gitu dapat bola enakeun teh"
## [28] "egi suruh latihan lebih banyak lagi next hugo samir jadi starter ðÿ\u0081"
## [29] "keren bet oshimen"
## [30] "keren tempaan bapaknya kalem akuratgol"
## [31] "mantap httpstcolaqsecx e ilp ffyub"
## [32] "kenceng kieu larinya"
## [33] "jacksen bangets"
## [34] "hugo samir naturalisasi ya"
## [35] "mantab timnasday httpstcoo a vcpnz"
## [36] "tidak disangka sangka"
## [37] "hugo calon bintang"
## [38] "untung bs menangsecara permainan msh berantakantdk ada pengatur serangan"
## [39] "gol pertamanya ada yg punya"
## [40] "ngelihat selebrasinya ngerasain dia bangga banget memakai jersey lambang dada"
## [41] "keren nii"
## [42] "mantab lanjutkan garuda muda"
## [43] "mantap garuda indonesiaaðÿª"
## [44] "tipcoineth tip"
## [45] "keren indonesia ku"
## [46] "mbappe versi lite"
## [47] "victor osimhen versi indonesia"
## [48] "titisan ronaldo sihðÿ"
## [49] " kompak masih sering salah passing golnya karena skill individu rumakiek blunder lawan plus kecepatan kecerdasan hugo"
## [50] "hugo anak baik anak soleh masyaallah sejak kecil ikutan sholat mamanya udh gede hafidz quran lo"
## [51] "hugo samir si wonderkid sepakbola indonesia ternyata penghafal alquran lho gak nyangka anak jacksen f thiago mantep juga yaa httpstcoegdqw kbd"
## [52] "semoga pemain timnas kita terus berkembang lebih baik lagi ketika umurnya dewasa nanti aamiin"
## [53] "mantap"
## [54] "mainnya gk ngalir krn tdk ada playmaker sprti beckham atau marselino alhamdulillah tetap bs meraih kemenangan"
## [55] "siaranbolalive alhamdulillah menang"
## [56] "bolanya mengelinding bebas keren"
## [57] "entah knp kok lht kyk permainan tarkam"
## [58] "kurang gregwt krn penonton nya sepibiasa rameklo main negara sendiri jd seru"
## [59] "hugo is the boss ðÿœ"
## [60] "mutiara hitam"
## [61] "goal nya macam taiwoawoniyi"
## [62] "gokil mbappe"
## [63] "keep strong and win kitagaruda timnasday garudamendunia tip"##Membuat Word Cloud komentar Positif #Mengubah Data Frame Menjadi Data Faktor
tdm_pos <- TermDocumentMatrix(komentar_positif)
tdm_pos## <<TermDocumentMatrix (terms: 323, documents: 63)>>
## Non-/sparse entries: 432/19917
## Sparsity : 98%
## Maximal term length: 17
## Weighting : term frequency (tf)m_pos <- as.matrix(tdm_pos)
View(m_pos)
v_pos <- sort(rowSums(m_pos),decreasing = TRUE)
head(v_pos)## hugo samir keren garuda indonesia timnas
## 12 7 7 7 6 6#Mengubah Data Faktor Menjadi Data Frame
d_pos <- data.frame(word = names(v_pos), freq = v_pos)
head(d_pos)## word freq
## hugo hugo 12
## samir samir 7
## keren keren 7
## garuda garuda 7
## indonesia indonesia 6
## timnas timnas 6wordcloud(d_pos$word, d_pos$freq,
random.order = FALSE,
max.words = 500,
colors = brewer.pal(name = "Dark2",8 ))
# Buat DataFrame hanya untuk komentar negatif
komentar_negatif <- databersih %>%
filter(komen == "negative")
komentar_negatif<-komentar_negatif$x
komentar_negatif## [1] "gue bilang juga coach is luckyne gede bgt"
## [2] "dulu pas dipersis kalo kelakukannya ga jabang bayik udah jadi super star ni bocah wkwk ytta aja wkwk"
## [3] "kek unexpected banget kirain mau dipegang sama kiperðÿ"
## [4] " siapa yg lg bakar jagung pas nonton bolaðÿž"
## [5] "cuma rada kasar dia mainnya harus ditatar dulu sama bapaknya ðÿ"
## [6] "kipernya terlalu cepat keluarðÿ"
## [7] "walaupun maennya ngantuk tapi stamina kita lebih bagus daripada kirjisgan"
## [8] "witan udah sering dapet kesempatan begini cm keberuntungannya setipis tissueðÿ"
## [9] "kualitas siarannya bolehlah"
## [10] "hahahakipernya kena tipu"
## [11] "setelah nonton pertandingan ternyata kirikgistan ga sejago itutimnas bikin ngantuk krn lucky aja iniðÿ"
## [12] "kalo witan mah gak gol "
## [13] "keren cmn tolong nih lain kali jangan terlalu byk maen dibelakang kecolongan baru tau"
## [14] "beruntung aja wkwk"
## [15] "ga perlu gocak gocek cari posisi untuk eksekusi"
## [16] "kasih starter line up napa jgn egy mulu haha"
## [17] "hubungi"
## [18] "top"
## [19] "jaga disiplin jangan lagi kau sepak wasit ya ðÿ\u0081"
## [20] " blunder bek lawan bukan konsep serangan balik"
## [21] "gara hugo samir indonesia kalah"
## [22] " liga tarkam kah gaenak banget diliat"
## [23] "masih ada bek yg posisinya sejajar kiper ngapain maju ðÿ "
## [24] "ahayðÿ"
## [25] "selebrasi dlu ygy sbelum bola masuk ke gawang ðÿðÿ\u008fðÿ\u008f"
## [26] "ampun dah bek nya masih recover tapi kipernyaa malah maju akwkaoakaokaoaka"
## [27] "selebrasi dluan sbelum gol"
## [28] "boring liat permaenan timnas"
## [29] "ya bapaknya ganas anaknya ga buat goal ðÿ\u0081"##Membuat Word Cloud komentar Negatif #Mengubah Data Frame Menjadi Data Faktor
tdm_neg <- TermDocumentMatrix(komentar_negatif)
tdm_neg## <<TermDocumentMatrix (terms: 173, documents: 29)>>
## Non-/sparse entries: 197/4820
## Sparsity : 96%
## Maximal term length: 16
## Weighting : term frequency (tf)m_neg <- as.matrix(tdm_neg)
View(m_neg)
v_neg <- sort(rowSums(m_neg),decreasing = TRUE)
head(v_neg)## aja wkwk bek dulu kalo pas
## 3 3 3 2 2 2#Mengubah Data Faktor Menjadi Data Frame
d_neg <- data.frame(word = names(v_neg), freq = v_neg)
head(d_neg)## word freq
## aja aja 3
## wkwk wkwk 3
## bek bek 3
## dulu dulu 2
## kalo kalo 2
## pas pas 2wordcloud(d_neg$word, d_neg$freq,
random.order = FALSE,
max.words = 500,
colors = brewer.pal(name = "Dark2",8 )) 
# Buat DataFrame hanya untuk komentar Neutral
komentar_neutral <- databersih %>%
filter(komen == "neutral")
komentar_neutral<-komentar_neutral$x
komentar_neutral## [1] "udah takut kirgistan mainnya sepadan sama uzbekistan eh ngak tahunya skillnya dibawah timnas kl pelatihnya sty babak aja udah bobol gol tuh kirgistan"
## [2] "lanjutkan jaga emosi jangan sampe kena hukuman komdis lagi"
## [3] "intsting ðÿ "
## [4] "reply isinya witan ðÿðÿðÿ jadi inget lawan thailand final tae"
## [5] "osimhen"
## [6] "ðÿðÿðÿðÿðÿðÿðÿ"
## [7] "jadi inget liverpool vs city"
## [8] "ronaldo ga ada ya"
## [9] "ðÿðÿðÿðÿðÿðÿðÿðÿðÿðÿðÿðÿ"
## [10] "akmaliaaf"
## [11] "ðÿðÿðÿ"
## [12] "mainmu saiki ajur"
## [13] "mudryk kudu liat "
## [14] "all naturalisasi timnas naturalisasi"
## [15] "klo mainnya msh kyk gini ngeri gk nanti ktmu korut"
## [16] "umpan lambung yg aku rindukan wkwk"
## [17] "witan harus liat "
## [18] "mun nu najongna dedikusnandar asup moalnya"
## [19] "jadi inget witan"
## [20] "keren golnya sekelas champion"
## [21] "skill"##Membuat Word Cloud komentar Neutral #Mengubah Data Frame Menjadi Data Faktor
tdm_neutral <- TermDocumentMatrix(komentar_neutral)
tdm_neutral## <<TermDocumentMatrix (terms: 80, documents: 21)>>
## Non-/sparse entries: 90/1590
## Sparsity : 95%
## Maximal term length: 24
## Weighting : term frequency (tf)m_neutral <- as.matrix(tdm_neutral)
View(m_neutral)
v_neutral <- sort(rowSums(m_neutral),decreasing = TRUE)
head(v_neutral)## inget jadi witan kirgistan mainnya timnas
## 3 3 3 2 2 2#Mengubah Data Faktor Menjadi Data Frame
d_neutral <- data.frame(word = names(v_neutral), freq = v_neutral)
head(d_neutral)## word freq
## inget inget 3
## jadi jadi 3
## witan witan 3
## kirgistan kirgistan 2
## mainnya mainnya 2
## timnas timnas 2wordcloud(d_neutral$word, d_neutral$freq,
random.order = FALSE,
max.words = 500,
colors = brewer.pal(name = "Dark2",8 )) 
## PEMBAGIAN DATA ## # set nilai random generator
set.seed(1234)
library(caret)## Loading required package: latticelibrary(Matrix)membagi data 80% training, 20% testing
bagi <- createDataPartition(databersih$komen, p = 0.8, list=F)
training<- databersih[bagi,]
head(training)## x
## 1 looks like african playing for indonesia should have played all african players
## 3 masuk ngegolim hugo samir✜
## 4 golnya keren amp tidak disangka sangka ðÿ\u008dðÿ
## 5 alhamdulillah menang
## 6 mantap garuda muda
## 7 garuda bangkit lagii
## komen
## 1 positive
## 3 positive
## 4 positive
## 5 positive
## 6 positive
## 7 positivetesting<- databersih[-bagi,]
View(testing)METODE VALIDASI
cross-validasi 5 lipat
control <- trainControl(method = "cv", number = 5, classProbs = TRUE)
control## $method
## [1] "cv"
##
## $number
## [1] 5
##
## $repeats
## [1] NA
##
## $search
## [1] "grid"
##
## $p
## [1] 0.75
##
## $initialWindow
## NULL
##
## $horizon
## [1] 1
##
## $fixedWindow
## [1] TRUE
##
## $skip
## [1] 0
##
## $verboseIter
## [1] FALSE
##
## $returnData
## [1] TRUE
##
## $returnResamp
## [1] "final"
##
## $savePredictions
## [1] FALSE
##
## $classProbs
## [1] TRUE
##
## $summaryFunction
## function (data, lev = NULL, model = NULL)
## {
## if (is.character(data$obs))
## data$obs <- factor(data$obs, levels = lev)
## postResample(data[, "pred"], data[, "obs"])
## }
## <bytecode: 0x0000022c3f0575a8>
## <environment: namespace:caret>
##
## $selectionFunction
## [1] "best"
##
## $preProcOptions
## $preProcOptions$thresh
## [1] 0.95
##
## $preProcOptions$ICAcomp
## [1] 3
##
## $preProcOptions$k
## [1] 5
##
## $preProcOptions$freqCut
## [1] 19
##
## $preProcOptions$uniqueCut
## [1] 10
##
## $preProcOptions$cutoff
## [1] 0.9
##
##
## $sampling
## NULL
##
## $index
## NULL
##
## $indexOut
## NULL
##
## $indexFinal
## NULL
##
## $timingSamps
## [1] 0
##
## $predictionBounds
## [1] FALSE FALSE
##
## $seeds
## [1] NA
##
## $adaptive
## $adaptive$min
## [1] 5
##
## $adaptive$alpha
## [1] 0.05
##
## $adaptive$method
## [1] "gls"
##
## $adaptive$complete
## [1] TRUE
##
##
## $trim
## [1] FALSE
##
## $allowParallel
## [1] TRUENAIVE BAYES
modelNB<-naiveBayes(komen~.,data = training)
head(modelNB)## $apriori
## Y
## negative neutral positive
## 24 17 51
##
## $tables
## $tables$x
## x
## Y blunder bek lawan bukan konsep serangan balik kalo witan gak gol
## negative 0.04166667 0.00000000
## neutral 0.00000000 0.00000000
## positive 0.00000000 0.01960784
## x
## Y kejayaan sepak bola indonesiasegera dimulai waktunya bersatu do' viking jakarta
## negative 0.00000000
## neutral 0.00000000
## positive 0.01960784
## x
## Y kompak masih sering salah passing golnya karena skill individu rumakiek blunder lawan plus kecepatan kecerdasan hugo
## negative 0.00000000
## neutral 0.00000000
## positive 0.01960784
## x
## Y liga tarkam kah gaenak banget diliat
## negative 0.04166667
## neutral 0.00000000
## positive 0.00000000
## x
## Y siapa yg lg bakar jagung pas nonton bolaðÿž ahayðÿ akmaliaaf
## negative 0.04166667 0.04166667 0.00000000
## neutral 0.00000000 0.00000000 0.05882353
## positive 0.00000000 0.00000000 0.00000000
## x
## Y alhamdulillah menang all naturalisasi timnas naturalisasi
## negative 0.00000000 0.00000000
## neutral 0.00000000 0.05882353
## positive 0.01960784 0.00000000
## x
## Y ampun dah bek nya masih recover tapi kipernyaa malah maju akwkaoakaokaoaka
## negative 0.04166667
## neutral 0.00000000
## positive 0.00000000
## x
## Y beruntung aja wkwk bolanya mengelinding bebas keren
## negative 0.04166667 0.00000000
## neutral 0.00000000 0.00000000
## positive 0.00000000 0.01960784
## x
## Y boring liat permaenan timnas cakep speed kencengðÿœ
## negative 0.04166667 0.00000000
## neutral 0.00000000 0.00000000
## positive 0.00000000 0.01960784
## x
## Y cuma rada kasar dia mainnya harus ditatar dulu sama bapaknya ðÿ
## negative 0.04166667
## neutral 0.00000000
## positive 0.00000000
## x
## Y dulu pas dipersis kalo kelakukannya ga jabang bayik udah jadi super star ni bocah wkwk ytta aja wkwk
## negative 0.04166667
## neutral 0.00000000
## positive 0.00000000
## x
## Y ðÿðÿðÿ ðÿðÿðÿðÿðÿðÿðÿ ðÿðÿðÿðÿðÿðÿðÿðÿðÿðÿðÿðÿ
## negative 0.00000000 0.00000000 0.00000000
## neutral 0.05882353 0.05882353 0.05882353
## positive 0.00000000 0.00000000 0.00000000
## x
## Y egi suruh latihan lebih banyak lagi next hugo samir jadi starter ðÿ\u0081
## negative 0.00000000
## neutral 0.00000000
## positive 0.01960784
## x
## Y entah knp kok lht kyk permainan tarkam
## negative 0.00000000
## neutral 0.00000000
## positive 0.01960784
## x
## Y ga perlu gocak gocek cari posisi untuk eksekusi
## negative 0.04166667
## neutral 0.00000000
## positive 0.00000000
## x
## Y gara hugo samir indonesia kalah garuda bangkit lagii
## negative 0.04166667 0.00000000
## neutral 0.00000000 0.00000000
## positive 0.00000000 0.01960784
## x
## Y gila larinye cepet banget goal nya macam taiwoawoniyi gokil mbappe
## negative 0.00000000 0.00000000 0.00000000
## neutral 0.00000000 0.00000000 0.00000000
## positive 0.01960784 0.01960784 0.01960784
## x
## Y gol pertamanya ada yg punya
## negative 0.00000000
## neutral 0.00000000
## positive 0.01960784
## x
## Y golnya keren amp tidak disangka sangka ðÿ\u008dðÿ
## negative 0.00000000
## neutral 0.00000000
## positive 0.01960784
## x
## Y good timnas ðÿðÿðÿðÿ\u008f good coach indra sjahfri biasa nya mreka klau timnas menang sty yg banggakan sampai muji gak ktulunganðÿ giliran coach lokal mreka mengakui para pmain timnas ah mata sty anðÿ
## negative 0.00000000
## neutral 0.00000000
## positive 0.01960784
## x
## Y hafidz quran nih anak keren respect hahahakipernya kena tipu
## negative 0.00000000 0.04166667
## neutral 0.00000000 0.00000000
## positive 0.01960784 0.00000000
## x
## Y hugo anak baik anak soleh masyaallah sejak kecil ikutan sholat mamanya udh gede hafidz quran lo
## negative 0.00000000
## neutral 0.00000000
## positive 0.01960784
## x
## Y hugo is the boss ðÿœ hugo samir naturalisasi ya
## negative 0.00000000 0.00000000
## neutral 0.00000000 0.00000000
## positive 0.01960784 0.01960784
## x
## Y hugo samir si wonderkid sepakbola indonesia ternyata penghafal alquran lho gak nyangka anak jacksen f thiago mantep juga yaa httpstcoegdqw kbd
## negative 0.00000000
## neutral 0.00000000
## positive 0.01960784
## x
## Y intsting ðÿ jadi inget liverpool vs city jadi inget witan
## negative 0.00000000 0.00000000 0.00000000
## neutral 0.05882353 0.05882353 0.05882353
## positive 0.00000000 0.00000000 0.00000000
## x
## Y kalo witan mah gak gol kasih starter line up napa jgn egy mulu haha
## negative 0.04166667 0.04166667
## neutral 0.00000000 0.00000000
## positive 0.00000000 0.00000000
## x
## Y keep strong and win kitagaruda timnasday garudamendunia tip
## negative 0.00000000
## neutral 0.00000000
## positive 0.01960784
## x
## Y kek unexpected banget kirain mau dipegang sama kiperðÿ
## negative 0.04166667
## neutral 0.00000000
## positive 0.00000000
## x
## Y kelebihan para pemain indonesia adalah speed kenceng
## negative 0.00000000
## neutral 0.00000000
## positive 0.01960784
## x
## Y kenceng kieu larinya keren bet oshimen keren indonesia ku keren nii
## negative 0.00000000 0.00000000 0.00000000 0.00000000
## neutral 0.00000000 0.00000000 0.00000000 0.00000000
## positive 0.01960784 0.01960784 0.01960784 0.01960784
## x
## Y kipernya terlalu cepat keluarðÿ
## negative 0.04166667
## neutral 0.00000000
## positive 0.00000000
## x
## Y klo mainnya msh kyk gini ngeri gk nanti ktmu korut
## negative 0.00000000
## neutral 0.05882353
## positive 0.00000000
## x
## Y kualitas siarannya bolehlah
## negative 0.04166667
## neutral 0.00000000
## positive 0.00000000
## x
## Y kurang gregwt krn penonton nya sepibiasa rameklo main negara sendiri jd seru
## negative 0.00000000
## neutral 0.00000000
## positive 0.01960784
## x
## Y laju banget akselerasinya
## negative 0.00000000
## neutral 0.00000000
## positive 0.01960784
## x
## Y lanjutkan jaga emosi jangan sampe kena hukuman komdis lagi
## negative 0.00000000
## neutral 0.05882353
## positive 0.00000000
## x
## Y looks like african playing for indonesia should have played all african players
## negative 0.00000000
## neutral 0.00000000
## positive 0.01960784
## x
## Y mainmu saiki ajur
## negative 0.00000000
## neutral 0.05882353
## positive 0.00000000
## x
## Y mainnya gk ngalir krn tdk ada playmaker sprti beckham atau marselino alhamdulillah tetap bs meraih kemenangan
## negative 0.00000000
## neutral 0.00000000
## positive 0.01960784
## x
## Y mantab lanjutkan garuda muda mantab timnasday httpstcoo a vcpnz
## negative 0.00000000 0.00000000
## neutral 0.00000000 0.00000000
## positive 0.01960784 0.01960784
## x
## Y mantap mantap garuda indonesiaaðÿª mantap garuda muda
## negative 0.00000000 0.00000000 0.00000000
## neutral 0.00000000 0.00000000 0.00000000
## positive 0.01960784 0.01960784 0.01960784
## x
## Y mantap garuda muda menang laga perdana asian games ðÿ\u008dðÿðÿ httpstcoaaryso ipz
## negative 0.00000000
## neutral 0.00000000
## positive 0.01960784
## x
## Y masih ada bek yg posisinya sejajar kiper ngapain maju ðÿ
## negative 0.04166667
## neutral 0.00000000
## positive 0.00000000
## x
## Y masuk ngegolim hugo samir✜ mbappe versi lite mudryk kudu liat
## negative 0.00000000 0.00000000 0.00000000
## neutral 0.00000000 0.00000000 0.05882353
## positive 0.01960784 0.01960784 0.00000000
## x
## Y mun nu najongna dedikusnandar asup moalnya mutiara hitam
## negative 0.00000000 0.00000000
## neutral 0.05882353 0.00000000
## positive 0.00000000 0.01960784
## x
## Y nah bener kayak ginidapat umpanbawa sat set sat set gol gak usah nekuk dulugak perlu gocek dulu modelan ivar jener nihayo pemain timnas biasakan kayak gitu dapat bola enakeun teh
## negative 0.00000000
## neutral 0.00000000
## positive 0.01960784
## x
## Y ngelihat selebrasinya ngerasain dia bangga banget memakai jersey lambang dada
## negative 0.00000000
## neutral 0.00000000
## positive 0.01960784
## x
## Y osimhen pemain mana hugo samir
## negative 0.00000000 0.00000000
## neutral 0.05882353 0.00000000
## positive 0.00000000 0.01960784
## x
## Y pemain potensial cuma dia sering emosian tinggal atasi terus berkembang
## negative 0.00000000
## neutral 0.00000000
## positive 0.01960784
## x
## Y reply isinya witan ðÿðÿðÿ jadi inget lawan thailand final tae
## negative 0.00000000
## neutral 0.05882353
## positive 0.00000000
## x
## Y ronaldo ga ada ya
## negative 0.00000000
## neutral 0.05882353
## positive 0.00000000
## x
## Y selebrasi dlu ygy sbelum bola masuk ke gawang ðÿðÿ\u008fðÿ\u008f
## negative 0.04166667
## neutral 0.00000000
## positive 0.00000000
## x
## Y selebrasi dluan sbelum gol
## negative 0.04166667
## neutral 0.00000000
## positive 0.00000000
## x
## Y semoga pemain timnas kita terus berkembang lebih baik lagi ketika umurnya dewasa nanti aamiin
## negative 0.00000000
## neutral 0.00000000
## positive 0.01960784
## x
## Y siaranbolalive alhamdulillah menang skill the next osimhen
## negative 0.00000000 0.00000000 0.00000000
## neutral 0.00000000 0.05882353 0.00000000
## positive 0.01960784 0.00000000 0.01960784
## x
## Y tipcoineth tip titisan ronaldo sihðÿ top
## negative 0.00000000 0.00000000 0.04166667
## neutral 0.00000000 0.00000000 0.00000000
## positive 0.01960784 0.01960784 0.00000000
## x
## Y untung bs menangsecara permainan msh berantakantdk ada pengatur serangan
## negative 0.00000000
## neutral 0.00000000
## positive 0.01960784
## x
## Y victor osimhen versi indonesia
## negative 0.00000000
## neutral 0.00000000
## positive 0.01960784
## x
## Y walaupun maennya ngantuk tapi stamina kita lebih bagus daripada kirjisgan
## negative 0.04166667
## neutral 0.00000000
## positive 0.00000000
## x
## Y witan udah sering dapet kesempatan begini cm keberuntungannya setipis tissueðÿ
## negative 0.04166667
## neutral 0.00000000
## positive 0.00000000
## x
## Y ya bapaknya ganas anaknya ga buat goal ðÿ\u0081 yukk garuda
## negative 0.04166667 0.00000000
## neutral 0.00000000 0.00000000
## positive 0.00000000 0.01960784
##
##
## $levels
## [1] "negative" "neutral" "positive"
##
## $isnumeric
## x
## FALSE
##
## $call
## naiveBayes.default(x = X, y = Y, laplace = laplace)#Melakukan Prediksi Menggunakan Data Testing
prediksiNB_test<-predict(modelNB,testing)
hasil_testNB=confusionMatrix(table(prediksiNB_test,testing$komen))
hasil_testNB## Confusion Matrix and Statistics
##
##
## prediksiNB_test negative neutral positive
## negative 0 0 0
## neutral 0 0 0
## positive 5 4 12
##
## Overall Statistics
##
## Accuracy : 0.5714
## 95% CI : (0.3402, 0.7818)
## No Information Rate : 0.5714
## P-Value [Acc > NIR] : 0.5909
##
## Kappa : 0
##
## Mcnemar's Test P-Value : NA
##
## Statistics by Class:
##
## Class: negative Class: neutral Class: positive
## Sensitivity 0.0000 0.0000 1.0000
## Specificity 1.0000 1.0000 0.0000
## Pos Pred Value NaN NaN 0.5714
## Neg Pred Value 0.7619 0.8095 NaN
## Prevalence 0.2381 0.1905 0.5714
## Detection Rate 0.0000 0.0000 0.5714
## Detection Prevalence 0.0000 0.0000 1.0000
## Balanced Accuracy 0.5000 0.5000 0.5000