I am using TF-IDF for text classification and have been curious about the following two concepts.

The augmented term frequency which is basically used for weighting in order to eliminate the bias towards longer documents.

On the other hand, there is a cosine normalization which appears to be done for the same purpose.

Are they both similar? Can we use any one of them to eliminate the bias towards larger documents?


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.