Communication Dans Un Congrès Année : 2024

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

Résumé

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.

Fichier principal
Vignette du fichier
2024.nlpaics-1.2-Explainability_profiling.pdf (315.66 Ko) Télécharger le fichier
Origine Fichiers éditeurs autorisés sur une archive ouverte
Licence

Dates et versions

hal-05311130 , version 1 (13-10-2025)

Licence

Identifiants

  • HAL Id : hal-05311130 , version 1

Citer

Dana Rœmling, Yves Scherrer, Aleksandra Miletić. Explainability of machine learning approaches in forensic linguistics: a case study in geolinguistic authorship profiling. Proceedings of the First International Conference on Natural Language Processing and Artificial Intelligence for Cyber Security, Jul 2024, Lancaster, United Kingdom. ⟨hal-05311130⟩

Collections

35 Consultations
58 Téléchargements

Partager

  • More