Lauera1 Posted April 17 Share Posted April 17 I have a column with user entered comments so there is a lot of inconsistency between entries. However, I would like to be able to see if there are common words used between comments. I have seen other word clouds programs have the ability to choose 1-3 word commonalities amongst free text fields. Is there a way to do this with the Spotfire Word Cloud Mod or is there a different visualization that would work better for this application? Thanks in advance! Link to comment Share on other sites More sharing options...
Sweta Kotha Posted April 17 Share Posted April 17 Hi! It sounds like some natural language processing could help. Below is a community link for the spotfire-dsml python library; specifically the nlp_preprocessing submodule would be helpful. The 1-3 word commonalities are referred to as N-grams (unigrams, bigrams, trigrams, etc.). I attached a sfd file (this is also in the exchange component of spotfire-dsml) that can be directly uploaded into a Spotfire data function to get these N-gram features. Then, you'd use the Word cloud to visualize these features. All you need to specify in the 'Edit Parameters' section is the text column name, ID column, and perhaps modify the N-gram size/range (if you want more than trigrams or 1-3 common words - this can be higher but the default is 3) [Modeling] NLP Python Toolkit - Features.sfd Link to comment Share on other sites More sharing options...
Recommended Posts
Create an account or sign in to comment
You need to be a member in order to leave a comment
Create an account
Sign up for a new account in our community. It's easy!
Register a new accountSign in
Already have an account? Sign in here.
Sign In Now