Due to recent updates, all users are required to create an Altair One account to login to the RapidMiner community. Click the Register button to create your account using the same email that you have previously used to login to the RapidMiner community. This will ensure that any previously created content will be synced to your Altair One account. Once you login, you will be asked to provide a username that identifies you to other Community users. Email us at Community with questions.

"Preprocessing of Comments for Sentiment Analysis"

AB26511AB26511 Member Posts: 11 Contributor II
edited June 2019 in Help
Team,

I want to do preprocessing of the Comments which I want to use further for Sentiment Analysis.
How I will be able to do Preprocessing (includes conversion of Comment to lower case, remove stopwords, remove punctuations [i,e, :,.# @etc]) from the comments which I had collected in .csv file.

Is the sentiment analysis possible in Rapidminer (i.e. Classify any particular comment into Positive or Negative sentiment)


Thanks,

Amit
Tagged:

Answers

  • MariusHelfMariusHelf RapidMiner Certified Expert, Member Posts: 1,869 Unicorn
    Hi Amit,

    you can do that with the text mining extension. For information and tutorials, please have a look at http://rapid-i.com/content/view/189/212/lang,en/

    There are videos which cover your exact problems.

    Best regards,
    Marius
  • LabiLabi Member Posts: 1 Learner III
    Hello,

    1. How I can connect Linguistic Tokens/Sentences, I tried this tokenization, but no results?

    2. How can I filter the text to show me only (more than ) 2 < total occurrences? 

    3. I am using Open WordNet Dictionary to read the WordNet folder locally from the directory?

    Thank you in advance,
    Labi
  • MariusHelfMariusHelf RapidMiner Certified Expert, Member Posts: 1,869 Unicorn
    Hi Labi!
    Labi wrote:

    1. How I can connect Linguistic Tokens/Sentences, I tried this tokenization, but no results?
    What do you mean be "connect"? What does "no result" mean? As always, it may be a good idea to describe more detailed what you expect and attach your process xml as explained in my signature.

    2. How can I filter the text to show me only (more than ) 2 < total occurrences? 
    Again, please describe more detailed what you want to do.

    3. I am using Open WordNet Dictionary to read the WordNet folder locally from the directory?
    I don't know what you are doing, but did you try out our wordnet extension? Maybe that already helps? It's available from the marketplace at http://marketplace.rapid-i.com

    Sorry for answering your questions with only more questions, but I need more info ;)

    Best regards,
    Marius
Sign In or Register to comment.