I want a code that detects compound words atomatically in the corpus and display in the dtm like "BigData", "SocialMedia", "SentimentAnalysis", "GoodMorning" and not "big", "data", "social" ... separately.
Do I have to define the compound words in input or is there a statistical function which detects its words?
This topic was automatically closed 21 days after the last reply. New replies are no longer allowed.