What is the best Model for website page categorization

davidellisdavidellis Member Posts: 4 Contributor I
My challenge is to convert web pages to word vectors and then categorize them into two groups, one set of pages that contain Online Education and one set of pages that do not contain continuing education.

My model works OK using the SVM module but wonder if anyone can recommend a better module (without me having to try them all

Thanks in advance.

Answers

  • MartinLiebigMartinLiebig Administrator, Moderator, Employee, RapidMiner Certified Analyst, RapidMiner Certified Expert, University Professor Posts: 3,503 RM Data Scientist
    Hi,

    there is a theorem called "No free lunch". Noone can tell you before hand what works best. My guess would have been an SVM.

    ~Martin
    - Sr. Director Data Solutions, Altair RapidMiner -
    Dortmund, Germany
  • davidellisdavidellis Member Posts: 4 Contributor I
    So far that is what I have found!! others are great at finding the no's but not so hot on the yess
  • MartinLiebigMartinLiebig Administrator, Moderator, Employee, RapidMiner Certified Analyst, RapidMiner Certified Expert, University Professor Posts: 3,503 RM Data Scientist
    yep.

    My personal next step would be preprocessing
    - Pruning
    - Stemming
    - n-gram
    and stuff like Feature selection. E.g. Weight by SVM.

    ~Martin
    - Sr. Director Data Solutions, Altair RapidMiner -
    Dortmund, Germany
Sign In or Register to comment.