Importing large directory of MS Word and .pdf files to KNIME

I’m looking for help building a workflow that would start with importing text from a large directory of MS Word and .pdf files. This data would be used for topic modelling, tagging, and deep learning. At a minimum I’d like to get this data into KNIME, but any direction on the text processing and approaches would be appreciated.

Look at the

and other nodes around.

Have you searched on the Hub for example workflows? There are several. In particular you might try:

Topic Modeling:
Document Tagging:
Sentiment Analysis w/ Deep Learning: