Separating Style from Substance: Enhancing Cross-Genre Authorship Attribution through Data Selection and Presentation
This addresses the problem of authorship attribution across different genres for forensic or literary analysis, though it appears incremental as it refines existing approaches.
The paper tackled the challenge of cross-genre authorship attribution by proposing methods to reduce reliance on topic information, resulting in a 62.7% relative improvement in cross-genre performance and 16.6% in per-genre conditions.
The task of deciding whether two documents are written by the same author is challenging for both machines and humans. This task is even more challenging when the two documents are written about different topics (e.g. baseball vs. politics) or in different genres (e.g. a blog post vs. an academic article). For machines, the problem is complicated by the relative lack of real-world training examples that cross the topic boundary and the vanishing scarcity of cross-genre data. We propose targeted methods for training data selection and a novel learning curriculum that are designed to discourage a model's reliance on topic information for authorship attribution and correspondingly force it to incorporate information more robustly indicative of style no matter the topic. These refinements yield a 62.7% relative improvement in average cross-genre authorship attribution, as well as 16.6% in the per-genre condition.