CLG Authorship Analytics: a library for authorship verification

The task of authorship verification consists in detecting whether two texts have been written by the same person. This paper describes CLG Authorship Analytics software, which implements several individual methods as well a stacked generalization system for verification. approach relies primarily on ensemble learning methods, i.e. repeatedly sampling data order to capture invariant stylistic patterns. is tested through series experiments designed test ability generalize, depending various parameters. code and results are publicly available https://github.com/erwanm/clg-authorship-experiments .