# The Topic Confusion Task: A Novel Scenario for Authorship Attribution

arXiv: https://arxiv.org/abs/2104.08530 · HTML: https://mlsanity.com/paper/2104.08530/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 44 references that are in the map.
- First posted on arXiv 17 Apr 2021.

## Builds on (most cited first, 5 of 5)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Deep contextualized word representations](https://mlsanity.com/paper/1802.05365/) (2018)
- [Learning Stylometric Representations for Authorship Analysis](https://mlsanity.com/paper/1606.01219/) (2016)

## Built on by (most cited first, 17 of 17)

- [On the State of the Art in Authorship Attribution and Authorship Verification](https://mlsanity.com/paper/2209.06869/) (2022)
- [The Project Dialogism Novel Corpus: A Dataset for Quotation Attribution in Literary Texts](https://mlsanity.com/paper/2204.05836/) (2022)
- [Understanding writing style in social media with a supervised contrastively pre-trained transformer](https://mlsanity.com/paper/2310.11081/) (2023)
- [Leveraging Multilingual Training for Authorship Representation: Enhancing Generalization across Languages and Domains](https://mlsanity.com/paper/2509.16531/) (2025)
- [A comparison of several AI techniques for authorship attribution on Romanian texts](https://mlsanity.com/paper/2211.05180/) (2022)
- [Generalizability of Mixture of Domain-Specific Adapters from the Lens of Signed Weight Directions and its Application to Effective Model Pruning](https://mlsanity.com/paper/2402.10639/) (2024)
- [Reproduction and Replication of an Adversarial Stylometry Experiment](https://mlsanity.com/paper/2208.07395/) (2022)
- [BERT-based Authorship Attribution on the Romanian Dataset called ROST](https://mlsanity.com/paper/2301.12500/) (2023)
- [Addressing Topic Leakage in Cross-Topic Evaluation for Authorship Verification](https://mlsanity.com/paper/2407.19164/) (2024)
- [A stylometric analysis of speaker attribution from speech transcripts](https://mlsanity.com/paper/2512.13667/) (2025)
- [A Unified Evaluation Framework for Novelty Detection and Accommodation in NLP with an Instantiation in Authorship Attribution](https://mlsanity.com/paper/2305.05079/) (2023)
- [Authorship identification under domain shift: a survey of stylistic measures and learned author representations](https://mlsanity.com/paper/2310.00436/) (2023)
- [HALvest-Contrastive: Retrieval-Like Authorship Attribution with Patch-Level Late Interaction](https://mlsanity.com/paper/2407.20595/) (2024)
- [Explainable Disentangled Representation Learning for Generalizable Authorship Attribution in the Era of Generative AI](https://mlsanity.com/paper/2604.21300/) (2026)
- [Silencing the Risk, Not the Whistle: A Semi-automated Text Sanitization Tool for Mitigating the Risk of Whistleblower Re-Identification](https://mlsanity.com/paper/2405.01097/) (2024)
- [Stylometric Defenses Against Author Impersonation in Software Repositories](https://mlsanity.com/paper/2608.02695/) (2026)
- [Privacy Personalization Trade offs in LLMs: The Impact of Stylometric Signal Reduction on User-Specific Text Generation](https://mlsanity.com/paper/2609.22112/) (2026)

## Abstract (arXiv)

Authorship attribution is the problem of identifying the most plausible author of an anonymous text from a set of candidate authors. Researchers have investigated same-topic and cross-topic scenarios of authorship attribution, which differ according to whether new, unseen topics are used in the testing phase. However, neither scenario allows us to explain whether errors are caused by a failure to capture authorship writing style or by a topic shift. Motivated by this, we propose the topic confusion task where we switch the author-topic configuration between the training and testing sets. This setup allows us to distinguish two types of errors: those caused by the topic shift and those caused by the features' inability to capture the writing styles. We show that stylometric features with part-of-speech tags are the least susceptible to topic variations. We further show that combining them with other features leads to significantly lower topic confusion and higher attribution accuracy. Finally, we show that pretrained language models such as BERT and RoBERTa perform poorly on this task and are surpassed by simple features such as word-level n-grams.