Anaylize Comment Data from Facebook

Gloria_FockGloria_Fock MemberPosts:3Contributor I
edited December 2018 inHelp

Hello Rapidminer community!

I have been trying to figure out for some days how to:
1. Pull comments from Facebook posts into Rapidminer (Solved!)
2. Use that post text to extract keywords and the corresponding sentiment (including number of times a keyword is mentioned and the number of times it had a positive / negative / neutral usage).

The 1st step has already been solved. It is the 2nd that I am having issues with. I have already been able to get the sentiment for each comment but extrcting the keywords as been an issue. I would like the information to output like the process in this link:

http://blog.aylien.com/building-a-text-analysis-process-for-customer-reviews-in-rapidminer/

我附上了图片数据的提取ed from Facebook so you can understand where I am beginning. Also included is the csv of this information.

Screen Shot 2018-01-25 at 16.52.03.png

Any help would be greatly appriciated!
Sincerely,
Gloria

Tagged:

Best Answer

  • sgenzersgenzer Administrator, Moderator, Employee, RapidMiner Certified Analyst, Community Manager, Member, University Professor, PM ModeratorPosts:2,959Community Manager
    Solution Accepted

    hello@Gloria_Fock- great. That makes life a lot easier. This should get you in a good direction. You'll have to reset the Aylien connections back to yours and the csv to where it is stored on your computer.







    <运营商激活= " true " class = "过程”兼容ibility="8.0.001" expanded="true" name="Process">













    <参数键=“3”值= " object_id.true.polynominal.attribute"/>






























































    Scott

    Gloria_Fock

Answers

  • sgenzersgenzer Administrator, Moderator, Employee, RapidMiner Certified Analyst, Community Manager, Member, University Professor, PM ModeratorPosts:2,959Community Manager

    hello@Gloria_Fockwelcome to the community! I'd recommend posting your XML process here (see "Read Before Posting" on right when you reply). This way we can replicate what you're doing and help you better.

    Scott

    Gloria_Fock
  • Gloria_FockGloria_Fock MemberPosts:3Contributor I

    Here we go!

    This is just the part where I input the Facebook comments from a database and process the sentiment. I would like to then take the output from this process and make it look like the data in this tutorial.

    http://blog.aylien.com/building-a-text-analysis-process-for-customer-reviews-in-rapidminer/

    The author has posted his sample process at the bottom. I have been trying to make this work for days now but this is a bit above my pay grade :womanembarrassed: so any help would be appreciated!

    Sincerely,
    Gloria







    <运营商激活= " true " class = "过程”兼容ibility="8.0.001" expanded="true" name="Process">




























  • sgenzersgenzer Administrator, Moderator, Employee, RapidMiner Certified Analyst, Community Manager, Member, University Professor, PM ModeratorPosts:2,959Community Manager

    oh and you do know that we have a Facebook operator now, right?:)

    https://marketplace.www.turtlecreekpls.com/UpdateServer/faces/product_details.xhtml?productId=rmx_facebook

    Scott

  • Gloria_FockGloria_Fock MemberPosts:3Contributor I

    Hi Scott!

    I would like to thank you for your prompt reply and the helpful answer! This has indeed worked for what I am attempting to use Rapidminer for. As for the Facebook operator, I was only able to get it to return a maximum of 25 results per query. Instead, I used Facepager to extract the data I needed from Facebook.

    Thanks again and have a great weekend,
    Gloria

  • sgenzersgenzer Administrator, Moderator, Employee, RapidMiner Certified Analyst, Community Manager, Member, University Professor, PM ModeratorPosts:2,959Community Manager

    oh good! And...what is Facepager?:)


    Scott

Sign InorRegisterto comment.