解读主题

R 文本分析入门

Maham Faisal Khan

Senior Data Science Content Developer

两个主题

lda_topics <- LDA(
  dtm_review,
  k = 2,
  method = "Gibbs",
  control = list(seed = 42)
) %>% 
  tidy(matrix = "beta")

word_probs <- lda_topics %>% 
  group_by(topic) %>% 
  slice_max(beta, n = 15) %>% 
  ungroup() %>%
  mutate(term2 = fct_reorder(term, beta))

两个主题

ggplot(
  word_probs, 
  aes(
    term2, 
    beta, 
    fill = as.factor(topic)
  )
) +
  geom_col(show.legend = FALSE) +
  facet_wrap(~ topic, scales = "free") +
  coord_flip()

三个主题

lda_topics2 <- LDA(
  dtm_review,
  k = 3,
  method = "Gibbs",
  control = list(seed = 42)
) %>% 
  tidy(matrix = "beta")

word_probs2 <- lda_topics2 %>% 
  group_by(topic) %>% 
  slice_max(beta, n = 15) %>% 
  ungroup() %>%
  mutate(term2 = fct_reorder(term, beta))

三个主题

ggplot(
  word_probs2, 
  aes(
    term2, 
    beta, 
    fill = as.factor(topic)
  )
) +
  geom_col(show.legend = FALSE) +
  facet_wrap(~ topic, scales = "free") +
  coord_flip()

四个主题

模型选择的技巧

增加彼此不同的主题是好的
若开始重复主题，就过多了
根据高概率词的组合为主题命名

Vamos praticar!

R 文本分析入门