We want to analyse a huge number (n>10.000) of Documents with the “Term Co-Occurrence Counter”-node.
It seams like the node just analysis the same documents in a column and not different documents in the same row.
Is there a possibility to merge the cells / content of cells in a document-column into one cell as different Sections or Paragraphs, so we can analyse it with the Term Co-Occurrence Counter?
We created this example data set:
This is a simplified version of our workflow:
Is there a possibility to analyse the whole data-set by making one big Document out of the separated rows with this node?
In the best case, the content of the different cells are handled as individual sections or paragraphs. This would allow us to analysis the texts at different layers (Sections, Paragraphs, Sentences etc).
Or is there a different way to analyse the whole data-set?
Thanks for your help!