# Leveraging Discourse Information Effectively for Authorship Attribution

arXiv: https://arxiv.org/abs/1709.02271 · HTML: https://mlsanity.com/paper/1709.02271/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Sep 2017.

## Built on by (most cited first, 3 of 3)

- [TURINGBENCH: A Benchmark Environment for Turing Test in the Age of Neural Text Generation](https://mlsanity.com/paper/2109.13296/) (2021)
- [Linguistic and Embedding-Based Profiling of Texts generated by Humans and Large Language Models](https://mlsanity.com/paper/2507.13614/) (2025)
- [Authorship identification under domain shift: a survey of stylistic measures and learned author representations](https://mlsanity.com/paper/2310.00436/) (2023)

## Abstract (arXiv)

We explore techniques to maximize the effectiveness of discourse information in the task of authorship attribution. We present a novel method to embed discourse features in a Convolutional Neural Network text classifier, which achieves a state-of-the-art result by a substantial margin. We empirically investigate several featurization methods to understand the conditions under which discourse features contribute non-trivial performance gains, and analyze discourse embeddings.