# Explainability of machine learning approaches in forensic linguistics: a case study in geolinguistic authorship profiling

arXiv: https://arxiv.org/abs/2404.18510 · HTML: https://mlsanity.com/paper/2404.18510/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 35 references that are in the map.
- First posted on arXiv 29 Apr 2024.

## Builds on (most cited first, 8 of 8)

- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Language (Technology) is Power: A Critical Survey of "Bias" in NLP](https://mlsanity.com/paper/2005.14050/) (2020)
- [Understanding Neural Networks through Representation Erasure](https://mlsanity.com/paper/1612.08220/) (2016)
- [Automated Rationale Generation: A Technique for Explainable AI and its Effects on Human Perceptions](https://mlsanity.com/paper/1901.03729/) (2019)
- [Automatic Language Identification in Texts: A Survey](https://mlsanity.com/paper/1804.08186/) (2018)
- [Understanding Convolutional Neural Networks for Text Classification](https://mlsanity.com/paper/1809.08037/) (2018)
- [Extracting Lexical Features from Dialects via Interpretable Dialect Classifiers](https://mlsanity.com/paper/2402.17914/) (2024)

## Built on by (most cited first, 1 of 1)

- [Large Language Models and Forensic Linguistics: Navigating Opportunities and Threats in the Age of Generative AI](https://mlsanity.com/paper/2512.06922/) (2025)

## Abstract (arXiv)

Forensic authorship profiling uses linguistic markers to infer characteristics about an author of a text. This task is paralleled in dialect classification, where a prediction is made about the linguistic variety of a text based on the text itself. While there have been significant advances in recent years in variety classification, forensic linguistics rarely relies on these approaches due to their lack of transparency, among other reasons. In this paper we therefore explore the explainability of machine learning approaches considering the forensic context. We focus on variety classification as a means of geolinguistic profiling of unknown texts based on social media data from the German-speaking area. For this, we identify the lexical items that are the most impactful for the variety classification. We find that the extracted lexical features are indeed representative of their respective varieties and note that the trained models also rely on place names for classifications.