DesiFilter

DesiFilter extracts South Asian names from text.
Just paste in a news article, list of names, etc.

DesiFilter scans text for over 27,000 uniquely South Asian first and last names.

The current dataset is somewhat biased towards Indian and Pakistani names; I'd appreciate help in diversifying the name data. DesiFilter also tries to ignore common Anglo names, on the assumption that it will be used primarily in countries like the US, UK, Canada, etc., where you really don't want to indicate a match for every single John or Anthony.

DesiFilter was built to support community journalists, genealogists, and amateur researchers. Please let me know how you're using this, and if you'd like to see features like an API or RSS/Atom feed support.

Privacy note: I don't record what you're analyzing.

—Anirvan Chatterjee, feedback@desifilter.com

Run a search?

Bookmark on Delicious
Share on Facebook