I'd like to classify short documents, from a predefined set of words.

What algorithm would you suggest, LDA or pLSA ?

My use case

I have a list of users, and for each user a list of the pages she likes.

My goal is to classify users (documents) into classes (topics).

The documents are short, since a user is not likely to to like more than dozens of pages, and there are approximately 100k pages I care about

  • $\begingroup$ Could you give some more detail, like what is your goal? For what use is the classification? Is the classes also predefined, making it a classification problem, or undefined/unknown, making it into a clustering problem? Without some more information this cannot be answered. $\endgroup$ – kjetil b halvorsen Sep 7 '15 at 13:58
  • $\begingroup$ added some more data on my use case $\endgroup$ – Uri Goren Sep 8 '15 at 9:01
  • $\begingroup$ Topic modeling for short documents is discussed here: stats.stackexchange.com/questions/25558/… $\endgroup$ – Piotr Migdal Mar 6 '16 at 11:58

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.