This repo contains the machine learning model which got the 2th place to the PAN19 shared task Cross Domain Authorship Attribution.
After the competition a paper was published and presented at the CLEF conference. The model is based of a series of SVM's trained on different features, the predictions of those SVM's are combined through stacking. In the paper we explain the model we used in details, it can be seen for free at this link.
If you find this code useful consider to cite this work.
@article{bacciu2019cross,
title={Cross-Domain Authorship Attribution Combining Instance-Based and Profile-Based Features},
author={Bacciu, Andrea and La Morgia, Massimo and Mei, Alessandro and Nemmi, Eugenio Nerio and Neri, Valerio and Stefa, Julinda},
year={2019}
}