I would like to suggest improving Text Mining capabilities to add functionalities for doing Node Relational Maps similar to those which can be found in these two webpages:
the pictures look to me like Inverted SOMs. This is also available in RapidMiner for generic types of data. Admittedly it doesn't look as nice, but suits all use cases and not only text:
Of course the id can be replaced with your text
This is reachable over the Data to Similarity Operator.
Thanks again for your suggestion. Can you explain a bit better what you are trying to achieve? As Sebastian mentioned, there is functionality where you can achieve something similar through similarity computation. Is that a feasible way? Or what did you expect to be able to do exactly with this?
Appreciate your feedback.
You must be a registered user to add a comment. If you've already registered, sign in. Otherwise, register and sign in.