نمذجة الموضوعات باستخدام LDA

ما هي نمذجة الموضوعات؟

# LDA key assumptions:
# 1. Each document is a mixture of K topics
# 2. Each topic is a distribution over all vocabulary words
# 3. Words are generated by first picking a topic, then a word from that topic

# Example: K=2 topics in a corpus about tech and cooking
# Topic 1 (Tech):    neural(0.15) python(0.12) algorithm(0.10) ...
# Topic 2 (Cooking): recipe(0.14) flour(0.11) bake(0.10) ...

# A document about 'AI-generated recipes' might be:
# 70% Topic 1 (Tech) + 30% Topic 2 (Cooking)

cat('LDA parameters:\n')
cat('K = number of topics (you choose)\n')
cat('alpha = document-topic sparsity prior\n')
cat('beta  = topic-word sparsity prior\n')

DocumentTermMatrix من tm

library(tm)

# Build a corpus from raw text
docs <- c(
  'machine learning neural networks training algorithms',
  'deep learning gradient backpropagation optimizer',
  'python scikit numpy pandas machine learning',
  'database sql tables indexes queries joins',
  'relational schema normalization foreign primary',
  'nosql mongodb document store redis queries'
)

corpus <- Corpus(VectorSource(docs))
corpus <- tm_map(corpus, removePunctuation)
corpus <- tm_map(corpus, removeWords, stopwords('english'))
corpus <- tm_map(corpus, stripWhitespace)

dtm <- DocumentTermMatrix(corpus)
cat('DTM shape:', nrow(dtm), 'docs x', ncol(dtm), 'terms\n')
cat('Sparsity: ', round(tm::sparsity(dtm) * 100, 1), '%\n')

cast_dtm من tidytext

library(tidytext)
library(dplyr)

# Tidy corpus
corpus <- tibble::tibble(
  doc_id = c(rep(1, 3), rep(2, 3), rep(3, 3), rep(4, 3)),
  text   = c(
    'neural networks deep learning training',
    'gradient descent backpropagation optimizer',
    'machine learning algorithms classification',
    'database sql tables queries indexes',
    'relational schema normalization joins',
    'foreign primary key constraints transactions',
    'recipe bake flour butter oven',
    'cooking temperature simmer saute ingredients',
    'kitchen knife herbs spices garnish'
  )
)

dtm <- corpus |>
  unnest_tokens(word, text) |>
  anti_join(tidytext::stop_words, by = 'word') |>
  count(doc_id, word) |>
  cast_dtm(doc_id, word, n)

cat('DTM:', nrow(dtm), 'docs x', ncol(dtm), 'terms\n')

LDA(dtm, k = 5): ملاءمة النموذج

library(tidytext)
library(dplyr)
library(topicmodels)

# Build DTM
corpus <- tibble::tibble(
  doc_id = c(rep(1,3), rep(2,3), rep(3,3), rep(4,3), rep(5,3), rep(6,3)),
  text = c(
    'neural networks deep gradient','backpropagation training optimizer','learning model layers',
    'database sql queries indexes','relational tables joins foreign','schema normalization constraints',
    'recipe flour bake butter','cooking temperature oven simmer','kitchen knife herbs spices'
  )[rep(c(1,2,3,4,5,6), each=1)]
)

dtm <- corpus |>
  unnest_tokens(word, text) |>
  count(doc_id, word) |>
  cast_dtm(doc_id, word, n)

# Fit LDA with k=3 topics
lda_model <- LDA(dtm, k = 3, control = list(seed = 42))
cat('LDA model fitted: k=3 topics\n')
cat('Class:', class(lda_model), '\n')

tidy(lda, matrix = 'beta'): احتمالات الموضوعات لكل كلمة

library(topicmodels)
library(tidytext)
library(dplyr)

# Using the built-in AssociatedPress dataset
data('AssociatedPress', package = 'topicmodels')

lda <- LDA(AssociatedPress[1:50, ], k = 4, control = list(seed = 1234))

# Per-word topic probabilities (beta)
beta_tbl <- tidy(lda, matrix = 'beta')
cat('Beta matrix rows:', nrow(beta_tbl), '\n')
cat('Columns:', names(beta_tbl), '\n')

# Top words per topic
top_terms <- beta_tbl |>
  group_by(topic) |>
  slice_max(beta, n = 5) |>
  ungroup()

cat('\nTop 5 words per topic:\n')
print(top_terms)

تصوير كلمات الموضوعات

library(topicmodels)
library(tidytext)
library(dplyr)
library(ggplot2)

data('AssociatedPress', package = 'topicmodels')
lda <- LDA(AssociatedPress[1:100, ], k = 4, control = list(seed = 42))

tidy(lda, matrix = 'beta') |>
  group_by(topic) |>
  slice_max(beta, n = 8) |>
  ungroup() |>
  mutate(term = reorder_within(term, beta, topic)) |>
  ggplot(aes(term, beta, fill = factor(topic))) +
    geom_col(show.legend = FALSE) +
    facet_wrap(~topic, scales = 'free') +
    scale_x_reordered() +
    coord_flip() +
    labs(x = NULL, y = 'Beta', title = 'Top Words per LDA Topic') +
    theme_minimal(base_size = 10)

tidy(lda, matrix = 'gamma'): احتمالات الموضوعات لكل مستند

library(topicmodels)
library(tidytext)
library(dplyr)

data('AssociatedPress', package = 'topicmodels')
lda <- LDA(AssociatedPress[1:30, ], k = 3, control = list(seed = 99))

# Per-document topic proportions (gamma)
gamma_tbl <- tidy(lda, matrix = 'gamma')
cat('Gamma matrix rows:', nrow(gamma_tbl), '\n')

# Dominant topic per document
dominant_topic <- gamma_tbl |>
  group_by(document) |>
  slice_max(gamma, n = 1) |>
  ungroup()

cat('\nDominant topic per document (first 8):\n')
print(head(dominant_topic, 8))

اختيار K: عدد الموضوعات

library(topicmodels)
library(tidytext)

data('AssociatedPress', package = 'topicmodels')

# Evaluate perplexity for K = 2, 3, 4, 5
k_values <- 2:5
perplexities <- vapply(k_values, function(k) {
  model <- LDA(AssociatedPress[1:50, ], k = k,
               control = list(seed = 42))
  perplexity(model)
}, numeric(1))

results <- data.frame(k = k_values, perplexity = round(perplexities, 1))
cat('Perplexity by K:\n')
print(results)
cat('\nNote: lower perplexity = better fit to training data\n')

تسمية الموضوعات

library(topicmodels)
library(tidytext)
library(dplyr)

data('AssociatedPress', package = 'topicmodels')
lda <- LDA(AssociatedPress[1:100, ], k = 4, control = list(seed = 7))

# Top 5 words per topic for manual labelling
tidy(lda, matrix = 'beta') |>
  group_by(topic) |>
  slice_max(beta, n = 5) |>
  summarise(top_words = paste(term, collapse = ', ')) |>
  print()

# After inspecting top words, assign human-readable labels
topic_labels <- tibble::tibble(
  topic = 1:4,
  label = c('Politics', 'Economy', 'Sports', 'Science')  # your interpretation
)

cat('\nTopic labels assigned (example):\n')
print(topic_labels)

تطبيق LDA على مجموعة نصوص مخصّصة

library(tidytext)
library(dplyr)
library(topicmodels)

# 9 documents across 3 latent topics
docs <- tibble::tibble(
  id   = 1:9,
  text = c(
    'machine learning neural deep training',
    'algorithm gradient backpropagation network',
    'python tensorflow keras model layers',
    'database sql relational tables queries',
    'joins indexes schema foreign primary',
    'transactions normalization constraints',
    'recipe ingredients bake flour butter',
    'cooking temperature simmer oven saute',
    'kitchen knife herbs spices garnish'
  )
)

dtm <- docs |>
  unnest_tokens(word, text) |>
  count(id, word) |>
  cast_dtm(id, word, n)

lda <- LDA(dtm, k = 3, control = list(seed = 123))

tidy(lda, 'beta') |>
  group_by(topic) |>
  slice_max(beta, n = 4) |>
  summarise(words = paste(term, collapse = ', ')) |>
  print()

قيود LDA

# LDA assumptions and limitations
limitations <- data.frame(
  Assumption = c(
    'Bag of words', 'Fixed K', 'Topic independence',
    'Static topics', 'No metadata'
  ),
  Alternative = c(
    'word2vec / BERT',
    'ldatuning for K selection',
    'CTM (Correlated Topic Model)',
    'DTM (Dynamic Topic Model)',
    'STM (Structural Topic Model)'
  )
)

print(limitations, row.names = FALSE)

تحقّق سريع

مراجعة: نمذجة الموضوعات باستخدام LDA

library(topicmodels)
library(tidytext)
library(dplyr)

data('AssociatedPress', package = 'topicmodels')
lda <- LDA(AssociatedPress[1:20, ], k = 2, control = list(seed = 1))

tidy(lda, 'beta') |>
  group_by(topic) |>
  slice_max(beta, n = 3) |>
  summarise(top_words = paste(term, collapse = ', ')) |>
  print()