Authorship Attribution Using Text Distortion
TL
TL;DR
A novel method is presented that enhances authorship attribution effectiveness by introducing a text distortion step before extracting stylometric measures to mask topic-specific information that is not related to the personal style of authors.
Abstract
Authorship attribution is associated with important applications in forensics and humanities research. A crucial point in this field is to quantify the personal style of writing, ideally in a way that is not affected by changes in topic or genre. In this paper, we present a novel method that enhances authorship attribution effectiveness by introducing a text distortion step before extracting stylometric measures. The proposed method attempts to mask topic-specific information that is not related to the personal style of authors. Based on experiments on two main tasks in authorship attribution, closed-set attribution and authorship verification, we demonstrate that the proposed approach can enhance existing methods especially under cross-topic conditions, where the training and test corpora do not match in topic.
References49 items
1
Domain Adaptation for Authorship Attribution: Improved Structural Correspondence Learning
2
Author Identification Using Multi-headed Recurrent Neural Networks
3
Computational authorship verification method attributes a new work to a major 2nd century African author
4
Improving NCD accuracy by combining document segmentation and document distortion
5