I'm working with a dataset that includes comments in multiple languages. In order to be able to push translation work in the right direction, we need to be able to identify the language the comment is using.
Is there a way to do this using, for example, existing character sets for particular languages, e.g. Japanese or Korean character sets, or particular words for other languages, e.g. Danish, Spanish?
Or is there maybe an API that can be called to check on the language?
Thanks.