Document/feature similarity

require(quanteda)
require(quanteda.textstats)

textstat_dist() calculates similarities of documents or features for various measures. The output is compatible with R’s dist(), so hierarchical clustering can be performed without any transformation.

toks_inaug <- tokens(data_corpus_inaugural)
dfmat_inaug <- dfm(toks_inaug, remove = stopwords("en"))
## Warning: 'remove' is deprecated; use dfm_remove() instead
tstat_dist <- as.dist(textstat_dist(dfmat_inaug))
clust <- hclust(tstat_dist)
plot(clust, xlab = "Distance", ylab = NULL)