Given a list of phrases, count how many documents they appear in and subdivide by positive and negative appearance.
make.count.table(phrases, labeling, corpus)
List of strings
Vector of +1/0/-1 labels
A corpus object from tm package
This method does not consider multiple counts of phrases within documents.
Phrases can have wildcards and stemming notation. See
a dataframe of statistics. per.pos is the percent of the documents with the phrase that are positively labeled. per.tag is the percent of the positively labeled documents that have the phrase.
1 2 3 4