TFIDF

Pengantar Natural Language Processing di R

Kasey Jones

Research Data Scientist

Kelemahan bag-of-words

t1 <- "My name is John. My best friend is Joe. We like tacos."
t2 <- "Two common best friend names are John and Joe."
t3 <- "Tacos are my favorite food. I eat them with my buddy Joe."

clean_t1 <- "john friend joe tacos"
clean_t2 <- "common friend john joe names"
clean_t3 <- "tacos favorite food eat buddy joe"

Berbagi kata umum

clean_t1 <- "john friend joe tacos"
clean_t2 <- "common friend john joe names"
clean_t3 <- "tacos favorite food eat buddy joe"

Bandingkan t1 dan t2

3/4 kata dari t1 ada di t2
3/5 kata dari t2 ada di t1

Bandingkan t1 dan t3

2/4 kata dari t1 ada di t3
2/6 kata dari t3 ada di t1

Tacos penting

t1 <- "My name is John. My best friend is Joe. We like tacos."
t2 <- "Two common best friend names are John and Joe."
t3 <- "Tacos are my favorite food. I eat them with my friend Joe."

Kata di tiap teks:

John: t1, t2
Joe: t1, t2, t3
Tacos: t1, t3

TFIDF

clean_t1 <- "john friend joe tacos"
clean_t2 <- "common friend john joe names"
clean_t3 <- "tacos favorite food eat buddy joe"

TF: Term Frequency
- Proporsi kata dalam teks yang merupakan term itu
- john adalah 1/4 kata di clean_t1, tf = .25
IDF: Inverse Document Frequency
- Bobot seberapa umum term di seluruh dokumen
- john ada di 3/3 dokumen, IDF = 0

Rumus IDF

$ IDF = log \frac{N}{n_{t}} $

N: jumlah dokumen dalam korpus
$n_{t}$: jumlah dokumen yang memuat term

Contoh:

IDF Taco: $log (\frac{3}{2}) = .405$
IDF Buddy: $log (\frac{3}{1}) = 1.10$
IDF John: $log (\frac{3}{3}) = 0$

TF + IDF

clean_t1 <- "john friend joe tacos"
clean_t2 <- "common friend john joe names"
clean_t3 <- "tacos favorite food eat buddy joe"

TFIDF untuk "tacos":

clean_t1: TF * IDF = (1/4) * (.405) = 0.101
clean_t2: TF * IDF = (0/4) * (.405) = 0
clean_t3: TF * IDF = (1/6) * (.405) = 0.068

Menghitung matriks TFIDF

# Create a data.frame
df <- data.frame('text' = c(t1, t2, t3), 'ID' = c(1, 2, 3))

df %>%
  unnest_tokens(output = "word", token = "words", input = text) %>%
  anti_join(stop_words) %>%
  count(ID, word, sort = TRUE) %>%
  bind_tf_idf(word, ID, n)

word: kolom yang memuat term
ID: kolom yang memuat ID dokumen
n: jumlah kata dari count()

Keluaran bind_tf_idf

# A tibble: 15 x 6
       X word         n    tf   idf tf_idf
   <dbl> <chr>    <int> <dbl> <dbl>  <dbl>
 1     1 friend       1 0.25  0.405 0.101 
 2     1 joe          1 0.25  0     0     
 3     1 john         1 0.25  0.405 0.101 
 4     1 tacos        1 0.25  0.405 0.101 
 5     2 common       1 0.2   1.10  0.220 
 6     2 friend       1 0.2   0.405 0.0811
 ...

Latihan TFIDF

Pengantar Natural Language Processing di R