corpus.format="plain" # "plain", "xml", "xml.drama", "xml.notitles", "html"
corpus.lang="English.all" # "English", "Polish", "French", "German", "Latin", Italian", Hungarian"
analyzed.features="w" # "w", "l"
ngram.size=1
random.sampling=FALSE
length.of.random.sample=10000
classification.method="knn" # "knn", "delta", "naivebayes", "nsc", "svm"
mfw.min=100
mfw.max=100
mfw.incr=100
start.at=1
mfw.list.cutoff=5000
culling.min=0 # from 0 to 100
culling.max=0 # from 0 to 100
culling.incr=20
delete.pronouns=FALSE
culling.of.all.samples=TRUE
final.ranking.of.candidates=TRUE
how.many.correct.attributions=TRUE
use.existing.freq.tables=TRUE
use.existing.wordlist=TRUE
distance.measure="CD" # "CD", "AL","ED","ES","MH", "CB","EU"
number.of.candidates=3
z.scores.of.all.samples=FALSE
reference.wordlist.of.all.samples=FALSE