Text Classification with Prevision.io

In this post we will show how in just a few minutes the Prevision.io It is known that textual data is usually more tricker and harder to process than the linear or categorical features. In fact, the linear features sometimes need to be scaled. Categorical features are scalar straightly encoded, but transforming texts into machine readable format requires a lot of pre-processing and feature engineering. Moreover, there are many other challenges that have to be addressed: how to cover different languages? How is it possible to preserve the semantic relationship between the words' vocabulary?