What is the process to remove words from a DTM when using the textmineR package in R for performing LDA?

edit

The process to remove words from a DTM before performing LDA using the textmineR package in R is as follows:

1. Create a Document Term Matrix (DTM) using the textmineR package. This can be done using the create_dtm() function.
2. Convert the DTM to a Term Document Matrix (TDM) using the t() function. This will transpose the matrix so that the words become rows and the documents become columns.
3. Calculate the document frequency of each word using the colSums() function. This will give you the number of documents in which each word appears.
4. Remove the words with a document frequency below a specified threshold. This can be done with the removeSparseTerms() function by setting the control argument to list(sparse = threshold).
5. Convert the TDM back to a DTM using the t() function again.
6. Normalize the DTM using the norm_dtm() function. This will transform the counts to relative frequencies.
7. Perform LDA on the cleaned DTM using the topicmodel() function.