The Altair Community is migrating to a new platform to provide a better experience for you. The RapidMiner Community will merge with the Altair Community at the same time. In preparation for the migration, both communities are on read-only mode from July 15th - July 24th, 2024. Technical support via cases will continue to work as is. For any urgent requests from Students/Faculty members, please submit the form linked here.
Options

Boolean Algebra

ZaramotZaramot Member Posts: 3 Newbie
Hello All. Im new to Rapidminer and using it for Textmining. I want to know if its possible to do boolean Algebra with it. Like i want to set 2 or more values. Something like "Customer" and "friendly". If these values appear in 1 sentence, than the textmining should show me the sentence and give it out. Is it possible to do something like that? I hope you can understand my english. It is not the greatest :)
thank you all in advance

Answers

  • Options
    MartinLiebigMartinLiebig Administrator, Moderator, Employee, RapidMiner Certified Analyst, RapidMiner Certified Expert, University Professor Posts: 3,525 RM Data Scientist

    what you can do is split into sentences and then 'missuse' the Dictionary Based Sentiment operator to create a 'flag'. Not sure if this is the most elegant version of it.

    And don't worry about your English. Its good. we can switch to German if needed though.

    Best,
    Martin
    - Sr. Director Data Solutions, Altair RapidMiner -
    Dortmund, Germany
  • Options
    ZaramotZaramot Member Posts: 3 Newbie
    Can you explain that in german to me pls?
  • Options
    MartinLiebigMartinLiebig Administrator, Moderator, Employee, RapidMiner Certified Analyst, RapidMiner Certified Expert, University Professor Posts: 3,525 RM Data Scientist
    edited August 2020

    ja klar. Was du machen kannst ist dein Dokument erst in Sätze aufteilen (Ich denke mit Cut Document?). Danach kannst du 'Dictionary Based Sentiment' "kreativ" einsetzen.
    Dictionary Based Sentiment geht einfach nur einmal über das Dokument und schaut ob bestimmte Wörter aus einem Wörterbuch vorhanden sind. Wenn ja dann summiert es die entsprechenden Gewichte auf. Der Gedanke hier ist, dass man positive Wörter zählt und dann weiss wie positiv der text ist.
    Du kannst halt einfach ein Wörterbuch der Form

    Word    Weight
    Customer   1
    friendly    1

    nutzen. Problematisch wirds erst wenn Wörter doppelt vorkommen etc. Da muss man dann direkt schauen.

    Alternativ kann man denke ich auch Generate Attrributes nutzen mit
    matches(Text,.*Customer.*)
    Ist halt die Frage was genau so vorkommen kann.

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