We can see that we almost achieve 60% accuracy on predicting the sentiment. For example, it is a hard task to know the meaning behind the word great; it could be used in a negative or positive context within a review.
To tackle this problem, we want to somehow create embeddings for the documents themselves and address the sentiment issue. Usually, a whole review is positive or a whole review is negative. We can use this to our advantage, and we will look at how to do this in the Using doc2vec for sentiment analysis recipe that follows.