The first example we are going to examine is a sentiment analysis case for movie reviews, the same as for the last example shown in the previous chapter (the Hands-on NLP with Spark-NLP section). The difference is that here, we are going to combine Word2Vec (https://en.wikipedia.org/wiki/Word2vec) and an RNN model.
Word2Vec can be seen as a neural network with two layers only, which expects as input some text content and then returns vectors. It isn't a deep neural network, but it is used to turn text into a numerical format that deep neural networks can understand. Word2Vec is useful because it can group the vectors of similar words together in a vector space. It does this mathematically. It creates, without human intervention, distributed numerical representations of word features. The vectors that represent words are called neural word embeddings...
