RapidMiner 9.7 is Now Available

Lots of amazing new improvements including true version control! Learn more about what's new here.

CLICK HERE TO DOWNLOAD

How to aggregate the polarity confidence and subjectivity confidence of individual tweets?

lambamanika07lambamanika07 Member Posts: 24  Maven
edited December 2019 in Help

aa.png

I want a single confidence level for each polarity and subjectivity. How to add up all the individual tweets polarity and subjectivity confidence?

Answers

  • Thomas_OttThomas_Ott RapidMiner Certified Analyst, RapidMiner Certified Expert, Member Posts: 1,761   Unicorn
    Have you tried the Aggregate operator?
    sgenzer
  • Telcontar120Telcontar120 Moderator, RapidMiner Certified Analyst, RapidMiner Certified Expert, Member Posts: 1,408   Unicorn

    As @Thomas_Ott says, this can be done with Aggregate, but have you thought about what that would actually mean?  It really isn't intuitive.  It would be the average confidence score across a number of distinct tweets, so you would need to be careful about how you interpreted that quantity.

    Brian T.
    Lindon Ventures 
    Data Science Consulting from Certified RapidMiner Experts
    sgenzer
  • HeikoeWin786HeikoeWin786 Member Posts: 30 Contributor II
    @lambamanika07
    Hello,
    May I know how do you get the subjectivity polarity?
    I want to calculate subjectivity for each of the user review comment in my excel. But, I am not sure which operator to be used in rapid miner.

    thanks.
  • lambamanika07lambamanika07 Member Posts: 24  Maven
    @HeikoeWin786 I used “Aylein” operator to perform sentiment analysis. You have to first download the “text analysis package”,  I guess from marketplace to get that operator and then put the API key into the operator just like Twitter operator. It allows sentiment analysis of around 1000 per day from one account. I hope that answer your question! 
    HeikoeWin786
  • HeikoeWin786HeikoeWin786 Member Posts: 30 Contributor II
    @lambamanika07 Thanks much :smiley: 
Sign In or Register to comment.