developed in order to be able to (i) precisely identify useful keywords and phrases that
characterize the input document and are relevant for the classification, (ii) normalize them to
avoid the dispersion of data caused by linguistic variation. That is, the main concern within the
DoRo project is to make use of NLP techniques to prove the intuition that NLP is a possible
solution … The duplicity of the objectives of the work is formally accounted for in the book as well …