1

I want to train a classifier with given names or surnames of different ethnic groups available in USA. I want to know if there are any open databases available or suggestions how we can create the database.

Improve this question

1 Answer 1

Reset to default
1

Voter rolls would be a fantastic place to look, the North Carolina State Board of Elections & Ethics Enforcement provides this data:

The North Carolina database includes race, ethnicity, and gender. It would be a good place for your classifier to train.

Improve this answer
3
  • There is no voter name in the field that you mentioned. I want to classify by names in to race, if the voter ID number is present I cannot use that. Instead can you provide the link to download ncvoter#.txt
    – Raady
    Commented Apr 4, 2018 at 13:00
  • @Raady I have updated the link to the one that has names.
    – Daniel Miller
    Commented May 8, 2018 at 15:26
  • do we have databases for other states as well ?
    – Raady
    Commented May 9, 2018 at 12:48

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.