What languages are supported

[gasyoun]

Is it English only?

[christofs]

No, many languages are supported, including Chinese, Japanese, Korean or Hebrew, Arabic, Cyrillic and Coptic, as long as your texts are in the UTF-8 encoding. See details here (page 10): https://github.com/computationalstylistics/stylo_howto/raw/master/stylo_howto.pdf

[Frenzie]

It depends a bit of the specific context you're thinking of. For basic tokenization just about anything goes, but for pronoun detection you might have to add your own.

stylo/man/stylo.pronouns.Rd

Lines 13 to 18 in c86fdb1

	\arguments{
	\item{corpus.lang}{an optional argument specifying the language of the texts
	analyzed: available languages are \code{English}, \code{Latin},
	\code{Polish}, \code{Dutch}, \code{French}, \code{German}, \code{Spanish},
	\code{Italian}, and \code{Hungarian} (default is \code{English}).}
	}