does anyone have any tips for using the tm package for supporting
autoclassifying textual documents? while tm works very well for
parsing text documents and creating term-document matrices, it doesnt
seem to support tracking document classes by default. without a way to
know the classes of your training documents, building a classifier is
kind of a non starter.
i know i could just do this manually by just reading in the classes
from a csv, but im hoping there is a fascility in tm for doing this
that im just missing.
thanks,
alan
