extract sentences and relate to a tag

cliors16

Hi. First of all I introduce myself, my name is Carlos from Colombia. I'm new to Rapidminer and I'm not very good at English either.

I thank who can help me.

I have a data set with two columns. The first column contains texts of labor profiles. The second column contains the salary.

I would like to create a model with RapidMiner to extract the most recurring job profiles, but I don't want keywords, but phrases or sentences. On the other hand, I would like to relate the results obtained with the salary (this could be done through a linear regression model, I think).

Somebody could help me?

Pavithra_Rao

Hi @cliors16

You could use the 'Process document operator' to create a word vector.
Word vector gives the table of all the words in the documents along with its frequency of the number of times each of this word appears in each document.

Here's a quick tutorial use case, on how to convert text into a dataset, that can be further used for modeling
https://academy.rapidminer.com/learn/video/applying-a-model-to-categorize-documents

Hope this helps.

Cheers,
Pavithra