Can+I+process+UTF-8+datasets+or+files?

= Can I process UTF-8 datasets/files? = Java can process UTF-8 files without any problems, it is just that Java uses a different encoding for displaying them under Windows (= "Cp1252"). If you change the file encoding to "utf-8" you'll be fine (discussed in [|this] WEKAlist post).

If you are running WEKA directly from the commandline, just add the following parameter to your commandline: > If you are starting WEKA from the Start menu, then edit the file:
 * If a placeholder already exists, then just change the value from "Cp1252" to "utf-8" (without the quotes of course).
 * If there isn't a yet, just the  parameter to all the / commands (see example  in [|this] post).