The data and models used into the experiment are organized as follow:
|---Disclosure_CNN - - - - - - - - Folder containing the Disclosure CNN model.
|---Disclosure_NER - - - - - - - - Folder containing the Named Entity Recognition model used to extract features.
|---Privacy_Dictionary - - - - - - - - Folder containing the privacy dictionary and the class in Python to use it.
|---Results_Distributions_N_times - - - - - - - - Folder containing the results distribution for each run of the experiment.
|---US_Dataset - - - - - - - - Folder containing the datasets used for the experiment.
|---5-fold Cross Valdiation N times sampling Dataset.ipynb - - - - - - - - Notebook containing the code to carry out N times the 5-fold cross validation with randomly sampled dataset each time.
|---Data Pre-Processing.ipynb - - - - - - - - Notebook containing the code to extract features from data and create the dataset for the experiment.
|---US_dataset.xlsx - - - - - - - - Dataset generated from "Data Pre-Processing.ipynb" notebook and used for the experiment in "5-fold Cross Valdiation N times sampling Dataset.ipynb".