In Latent Semantic Analysis, we get 3 matrices from the singular value decomposition (SVD), but I am confused - which matrix do we use for cosine similarity?

  • 1
    $\begingroup$ I do not vote this to close because for me it is very clear what the OP is asking. Having said that, I would suggest to the OP to actually write out what LSA is doing. I am pretty certain he will be able to answer his own question immediately afterwards; in particular he wants to examine the relation between PCA and SVD. $\endgroup$ – usεr11852 May 7 '15 at 7:47
  • $\begingroup$ This question may also be useful: stats.stackexchange.com/questions/134282/… $\endgroup$ – Alexey Grigorev May 7 '15 at 9:15

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.