# Idiosyncratic but not Arbitrary: Learning Idiolects in Online Registers Reveals Distinctive yet Consistent Individual Styles

arXiv: https://arxiv.org/abs/2109.03158 · HTML: https://mlsanity.com/paper/2109.03158/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 51 references that are in the map.
- First posted on arXiv 7 Sep 2021.

## Builds on (most cited first, 11 of 11)

- [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)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Proxy Anchor Loss for Deep Metric Learning](https://mlsanity.com/paper/2003.13911/) (2020)
- [ConvoKit: A Toolkit for the Analysis of Conversations](https://mlsanity.com/paper/2005.04246/) (2020)
- [Understanding Undesirable Word Embedding Associations](https://mlsanity.com/paper/1908.06361/) (2019)
- [Explainable Authorship Verification in Social Media via Attention-based Similarity Learning](https://mlsanity.com/paper/1910.08144/) (2019)
- [Issues in evaluating semantic spaces using word analogies](https://mlsanity.com/paper/1606.07736/) (2016)
- [Similarity Learning for Authorship Verification in Social Media](https://mlsanity.com/paper/1908.07844/) (2019)
- [You Write Like You Eat: Stylistic variation as a predictor of social stratification](https://mlsanity.com/paper/1907.07265/) (2019)
- [Digital Stylometry: Linking Profiles Across Social Networks](https://mlsanity.com/paper/1605.05166/) (2016)

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

- [LaMP: When Large Language Models Meet Personalization](https://mlsanity.com/paper/2304.11406/) (2023)
- [Can Large Language Models Transform Computational Social Science?](https://mlsanity.com/paper/2305.03514/) (2023)
- [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)
- [Tokenization is Sensitive to Language Variation](https://mlsanity.com/paper/2502.15343/) (2025)
- [VeriDark: A Large-Scale Benchmark for Authorship Verification on the Dark Web](https://mlsanity.com/paper/2207.03477/) (2022)
- [Leveraging Multilingual Training for Authorship Representation: Enhancing Generalization across Languages and Domains](https://mlsanity.com/paper/2509.16531/) (2025)
- [Can Authorship Attribution Models Distinguish Speakers in Speech Transcripts?](https://mlsanity.com/paper/2311.07564/) (2023)
- [Social Meme-ing: Measuring Linguistic Variation in Memes](https://mlsanity.com/paper/2311.09130/) (2023)
- [Online Personalizing White-box LLMs Generation with Neural Bandits](https://mlsanity.com/paper/2404.16115/) (2024)
- [VendorLink: An NLP approach for Identifying & Linking Vendor Migrants & Potential Aliases on Darknet Markets](https://mlsanity.com/paper/2305.02763/) (2023)
- [IDTraffickers: An Authorship Attribution Dataset to link and connect Potential Human-Trafficking Operations on Text Escort Advertisements](https://mlsanity.com/paper/2310.05484/) (2023)
- [On the Detectability of LLM-Generated Text: What Exactly Is LLM-Generated Text?](https://mlsanity.com/paper/2510.20810/) (2025)
- [Authorship identification under domain shift: a survey of stylistic measures and learned author representations](https://mlsanity.com/paper/2310.00436/) (2023)
- [Defending Against Authorship Identification Attacks](https://mlsanity.com/paper/2310.01568/) (2023)
- [The Many Voices of Duying: Revisiting the Disputed Essays Between Lu Xun and Zhou Zuoren](https://mlsanity.com/paper/2310.01440/) (2023)
- [Neurobiber: Fast and Interpretable Stylistic Feature Extraction](https://mlsanity.com/paper/2502.18590/) (2025)
- [Interpreting Style Representations via Style-Eliciting Prompts](https://mlsanity.com/paper/2606.05716/) (2026)

## Abstract (arXiv)

An individual's variation in writing style is often a function of both social and personal attributes. While structured social variation has been extensively studied, e.g., gender based variation, far less is known about how to characterize individual styles due to their idiosyncratic nature. We introduce a new approach to studying idiolects through a massive cross-author comparison to identify and encode stylistic features. The neural model achieves strong performance at authorship identification on short texts and through an analogy-based probing task, showing that the learned representations exhibit surprising regularities that encode qualitative and quantitative shifts of idiolectal styles. Through text perturbation, we quantify the relative contributions of different linguistic elements to idiolectal variation. Furthermore, we provide a description of idiolects through measuring inter- and intra-author variation, showing that variation in idiolects is often distinctive yet consistent.