stopwords("english")[1:5]
stopwords("italian")[1:5]
stopwords("arabic")[1:5]
# adding to the built-in stopword list
toks <- tokenize("The judge will sentence Mr. Adams to nine years in prison", removePunct = TRUE)
removeFeatures(toks, c(stopwords("english"), "will", "mr", "nine"))
Run the code above in your browser using DataLab