Style-aware Neural Model with Application in Authorship Attribution

TL;DR

This paper presents a style-aware neural model that encodes lexical, syntactic, and structural features of documents to improve authorship attribution accuracy, demonstrating benefits over existing methods on benchmark datasets.

Contribution

The paper introduces a novel neural model that jointly encodes lexical, syntactic, and structural stylistic features for authorship attribution.

Findings

Encoding all three stylistic levels improves attribution accuracy.

The hierarchical neural network effectively captures document structure.

Experimental results outperform baseline methods on four datasets.

Abstract

Writing style is a combination of consistent decisions associated with a specific author at different levels of language production, including lexical, syntactic, and structural. In this paper, we introduce a style-aware neural model to encode document information from three stylistic levels and evaluate it in the domain of authorship attribution. First, we propose a simple way to jointly encode syntactic and lexical representations of sentences. Subsequently, we employ an attention-based hierarchical neural network to encode the syntactic and semantic structure of sentences in documents while rewarding the sentences which contribute more to capturing the writing style. Our experimental results, based on four benchmark datasets, reveal the benefits of encoding document information from all three stylistic levels when compared to the baseline methods in the literature.