Search for only English pages

[MilesAheadAlso]

I'm trying to do sentiment analysis and obviously the sentiments are very language and even dialect dependent - Scottish vs English - so I'd like to retrieve pages with a certain language identifier only. I'm not sure this is even possible, but I thought I'd ask.

[nlch]

As far as I know there's no direct way to do that? You could search for pages with specific English keywords but that's no guarantee you won't get false positives...

The best approach is to either make a list of pages you KNOW are in English, or from some set of pages use a language detection package like textcat, cld2 or cld3 on the posts of the pages.

Hope that helps.