Purpose

This vignette creates a document-feature matrix from the corpus and filters it a number of tokens representing the country locations. Because the text mining is based on the text of the articles (that we cannot distribute), the vignette is not executed.

Extracting the document-feature matrix

library("magrittr")
filtered_dfm <- get_dfm() %>% filter_dfm()

filtering_tokens <- readRDS(system.file("extdata", "country_tokens.Rds", package = "wateReview"))
head(filtering_tokens)
#> [1] "argentina" "bahama"    "barbado"   "beliz"     "bolivia"   "brazil"

obj_dtm <- get_dtm(filtered_dfm, filtering_tokens)

Text mining

Purpose

Extracting the document-feature matrix