Text classifier by speech style
Hello. The task is to develop a text classifier based on the style of speech (artistic, journalistic, etc.). It is necessary to do this on the basis of a neural network. I can't determine the characteristics that determine the style of the text and figure out how to translate the source text into a vector of characteristics that the classifier will eventually work with.
How can this be done?
1 answers
Here is the table: 
(The table image is taken from from here)
As can be seen from it, in texts of different styles, either terms, or descriptions, or addresses, or slang or other Classes of words can prevail. The classes of words will be determined by the neural network after training. It will also define styles by recognizing the predominance of a certain class or combination of word classes in the text provided for recognition. The structure of the text will also be among the features (at least at the level of structured/not structured). And then-literature about training neural networks with reinforcement and training with a teacher.
The most important thing is the Error back propagation algorithm. (https://habrahabr.ru/post/154369/ - on Habr).