I'm looking for something written in a similar format as the famous Applied Predictive Modelling by Max Kuhn that would tackle topics such as:
- Creating document-term matrices, or DTMsm
- Creating term-co-occurrence matrices, or TCMs
- Creating GloVe word vectors from TCMs
- Creating a Word-Mover's-Distance model from GloVe vectors
- Applying Word-Mover's-Distance model to a pair of DTMs
I would like to wrap my ahead around the text2vec package but I feel I lack enough knowledge on building text mining classification models. Thanks!