Chapter 77 Word Cloud for Bigrams

We show the Fifty most important bigrams. This Word Cloud is based on the TF- IDF scores. Higher the score, bigger is the size of the text.

bigrams_united_withSeparator <- bigrams_filtered %>%
  unite(bigram, word1, word2, sep = "_")

bigram_tf_idf_withSeparator <- bigrams_united_withSeparator %>%
  dplyr::count(Results, bigram) %>%
  bind_tf_idf(bigram, Results, n) %>%
  arrange(desc(tf_idf))

bigram_tf_idf_withSeparator %>%
  with(wordcloud(bigram, tf_idf, max.words = 50,colors=brewer.pal(8, "Dark2")))

The bigrams shown are more informative than the single words. Example hazardous food , licensee 34 refer to some specific Results.