Given a sentence "I like blue jeans", the output should be "blue".

I do not have any training data. I'll just be downloading a bunch of tweets related to a hashtag.

How do I build a model for this? I haven't learnt word2vec but could that work? Pre-trained embeddings? I have not worked on them before yet but I want to know if it would work beforehand.

I want to know what would be the best approach and any references to similar problems worked on before. Thanks.

  • 2
    $\begingroup$ You can just prepare a list of such words which indicate color and search them in a sentence. I don't think there are more than 20 words for that. $\endgroup$ – Shubham Panchal Apr 12 '19 at 10:30
  • $\begingroup$ The purpose is to find colours that are trending for certain apparel. Colours may be something like "aquablue" or "stonewash" something like that. I'm looking to build something general that works. $\endgroup$ – Goutham Apr 12 '19 at 10:43
  • 3
    $\begingroup$ If that is the case, and if you're using Python, maybe package webcolors can be useful for you. Check out the accepted answer to this question. $\endgroup$ – GileBrt Apr 12 '19 at 11:30

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.