# The Importance of Suppressing Domain Style in Authorship Analysis

arXiv: https://arxiv.org/abs/2005.14714 · HTML: https://mlsanity.com/paper/2005.14714/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 May 2020.

## Built on by (most cited first, 18 of 18)

- [Same Author or Just Same Topic? Towards Content-Independent Style Representations](https://mlsanity.com/paper/2204.04907/) (2022)
- [Learning Interpretable Style Embeddings via Prompting LLMs](https://mlsanity.com/paper/2305.12696/) (2023)
- [On the State of the Art in Authorship Attribution and Authorship Verification](https://mlsanity.com/paper/2209.06869/) (2022)
- [Does It Capture STEL? A Modular, Similarity-based Linguistic Style Evaluation Framework](https://mlsanity.com/paper/2109.04817/) (2021)
- [O2D2: Out-Of-Distribution Detector to Capture Undecidable Trials in Authorship Verification](https://mlsanity.com/paper/2106.15825/) (2021)
- [Syllabic Quantity Patterns as Rhythmic Features for Latin Authorship Attribution](https://mlsanity.com/paper/2110.14203/) (2021)
- [A comparison of several AI techniques for authorship attribution on Romanian texts](https://mlsanity.com/paper/2211.05180/) (2022)
- [Grammar as a Behavioral Biometric: Using Cognitively Motivated Grammar Models for Authorship Verification](https://mlsanity.com/paper/2403.08462/) (2024)
- [SMAuC -- The Scientific Multi-Authorship Corpus](https://mlsanity.com/paper/2211.02477/) (2022)
- [BERT-based Authorship Attribution on the Romanian Dataset called ROST](https://mlsanity.com/paper/2301.12500/) (2023)
- [Layered Insights: Generalizable Analysis of Authorial Style by Leveraging All Transformer Layers](https://mlsanity.com/paper/2503.00958/) (2025)
- [IDIOLEX: Unified and Continuous Representations for Idiolectal and Stylistic Variation](https://mlsanity.com/paper/2604.04704/) (2026)
- [Authorship identification under domain shift: a survey of stylistic measures and learned author representations](https://mlsanity.com/paper/2310.00436/) (2023)
- [One-shot Style Transfer LLM log-probabilities for Authorship Attribution and Verification](https://mlsanity.com/paper/2510.13302/) (2025)
- [TraSE: Towards Tackling Authorial Style from a Cognitive Science Perspective](https://mlsanity.com/paper/2206.10706/) (2022)
- [Explainable Authorship Identification in Cultural Heritage Applications: Analysis of a New Perspective](https://mlsanity.com/paper/2311.02237/) (2023)
- [Neurobiber: Fast and Interpretable Stylistic Feature Extraction](https://mlsanity.com/paper/2502.18590/) (2025)
- [Text-to-Stage: Spatial Layouts from Long-form Narratives](https://mlsanity.com/paper/2603.17832/) (2026)

## Abstract (arXiv)

The prerequisite of many approaches to authorship analysis is a representation of writing style. But despite decades of research, it still remains unclear to what extent commonly used and widely accepted representations like character trigram frequencies actually represent an author's writing style, in contrast to more domain-specific style components or even topic. We address this shortcoming for the first time in a novel experimental setup of fixed authors but swapped domains between training and testing. With this setup, we reveal that approaches using character trigram features are highly susceptible to favor domain information when applied without attention to domains, suffering drops of up to 55.4 percentage points in classification accuracy under domain swapping. We further propose a new remedy based on domain-adversarial learning and compare it to ones from the literature based on heuristic rules. Both can work well, reducing accuracy losses under domain swapping to 3.6% and 3.9%, respectively.