"work with text"

ilya1985ilya1985 Member Posts: 1 Newbie
edited May 2019 in Help
Good morning. I working on the drafting ­of the patent landscape (inventions) and­ I want to highlight keywords from the t­ext using the program. Tell me please wh­at operators and in what sequence for th­is I should use?


  • Options
    rfuentealbarfuentealba Moderator, RapidMiner Certified Analyst, Member, University Professor Posts: 568 Unicorn
    Hello Ilya, and welcome to the Community.

    There is plenty of documentation and real good answers about this topic on this community site and other places. I will limit myself to give you some keywords so that you can do your own search and build your project.

    Normally you would use "Read Documents" to read the texts and make them available to the rest of the process. Then you might want to use "Process Documents" and inside this process you can: Tokenize, Filter Stopwords, Transform Cases and Generate N-Grams. These terms will help you with your search.

    Other keywords you should use in your search include "Natural Language Processing" and "NLP", as that is what you are doing.

    Old man's advice: we are willing to help but as data scientists and researchers, many of us encourage you to also do some research on your own and come up with problems when you get stuck. The best way to learn is to be hands on, no matter how wrong you get things over time. Making mistakes is part of the learning process. Go ahead!

    Hope this helps.

  • Options
    kypexinkypexin Moderator, RapidMiner Certified Analyst, Member Posts: 291 Unicorn
    Hi @ilya1985

    I suggest you to check this excellent tutorial from @Thomas_Ott about the similar topic, extracting key terms from tweets: 

    * http://www.neuralmarkettrends.com/use-rapidminer-discover-twitter-content/

    This approach is pretty much suited for your problem as well. 
Sign In or Register to comment.