CLG Authorship Analytics: a library for authorship verification - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue International Journal of Digital Humanities Année : 2022

CLG Authorship Analytics: a library for authorship verification

Erwan Moreau

Résumé

The task of authorship verification consists in detecting whether two texts have been written by the same person. This paper describes the CLG Authorship Analytics software, which implements several individual methods as well as a stacked generalization system for authorship verification. The approach relies primarily on ensemble learning methods, i.e. repeatedly sampling the data in order to capture the invariant stylistic patterns. The approach is tested through a series of experiments designed to test the ability of the system to generalize, depending on various parameters. The code and results of the experiments are publicly available.
Fichier principal
Vignette du fichier
main-1.pdf (254.21 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03912280 , version 1 (23-12-2022)

Identifiants

Citer

Erwan Moreau, Carl Vogel. CLG Authorship Analytics: a library for authorship verification. International Journal of Digital Humanities, 2022, ⟨10.1007/s42803-022-00051-w⟩. ⟨hal-03912280⟩
6 Consultations
35 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More