After pre-processing and cleaning the text in the Documents, we can now create their bag of words. All nodes preceding the Bag of Words part have been encapsulated in components, in order to make the workflow better readable. Comparing terms and lemmatized terms. Here we have 2 bags of words. One bag of words is created directly from the text in the documents; while the second bag of words is created from the same lemmatized document. The original terms and the corresponding lemmatized terms are then joined together.