Pengantar topic modeling

Pengantar Natural Language Processing di R

Kasey Jones

Research Data Scientist

Topic modeling

Kisah Olahraga:

skor
gosip pemain
berita tim
dll.

Cuaca di Zambia:

Latent Dirichlet Allocation

Dokumen adalah campuran topik
- Berita Tim 70%
- Gosip Pemain 30%
Topik adalah campuran kata
- Berita Tim: trade, pitcher, move, new
- Gosip Pemain: angry, change, money

Surat kabar berisi artikel yang berfokus pada topik tertentu.

¹ https://en.wikipedia.org/wiki/Latent_Dirichlet_allocation

Menyiapkan LDA

Persiapan awal:

animal_farm_tokens <- animal_farm %>%
  unnest_tokens(output = "word", token = "words", input = text_column) %>%
  anti_join(stop_words) %>%
  mutate(word = wordStem(word))

Matriks dokumen–term:

animal_farm_matrix <- animal_farm_tokens %>%
  count(chapter, word) %>%
  cast_dtm(document = chapter, term = word,
           value = n, weighting = tm::weightTf)

LDA

library(topicmodels)
animal_farm_lda <- LDA(train, k = 4, method = 'Gibbs',
                 control = list(seed = 1111))
animal_farm_lda

A LDA_Gibbs topic model with 4 topics.

Hasil LDA

animal_farm_betas <-
    tidy(animal_farm_lda, matrix = "beta")
animal_farm_betas

# A tibble: 11,004 x 3
   topic term         beta
   <int> <chr>       <dbl>
...
 5     1 abolish 0.0000360
 6     2 abolish 0.00129  
 7     3 abolish 0.000355 
 8     4 abolish 0.0000381
...

sum(animal_farm_betas$beta)

[1] 4

Kata teratas per topik

animal_farm_betas %>%
  group_by(topic) %>%
  slice_max(beta, n = 10) %>%
  arrange(topic, -beta) %>%
  filter(topic == 1)

   topic term          beta
   <int> <chr>        <dbl>
 1     1 napoleon   0.0339 
 2     1 anim       0.0317 
 3     1 windmil    0.0144 
 4     1 squealer   0.0119 
 ...

animal_farm_betas %>%
  group_by(topic) %>%
  slice_max(beta, n = 10) %>%
  arrange(topic, -beta) %>%
  filter(topic == 2)

   topic term        beta
   <int> <chr>      <dbl>
...
 3     2 anim     0.0189 
 ...
 6     2 napoleon 0.0148 
 ...

Kata teratas (lanj.)

Kita dapat membuat daftar kata teratas per topik dan memvisualisasikannya dengan ggplot.

¹ https://www.tidytextmining.com/topicmodeling.html

Melabeli dokumen sebagai topik

animal_farm_chapters <- tidy(animal_farm_lda, matrix = "gamma")
animal_farm_chapters %>%
  filter(document == 'Chapter 1')

# A tibble: 4 x 3
  document  topic  gamma
  <chr>     <int>  <dbl>
1 Chapter 1     1 0.157 
2 Chapter 1     2 0.136 
3 Chapter 1     3 0.623 
4 Chapter 1     4 0.0838

Latihan LDA!

Pengantar Natural Language Processing di R