37.1861, Software: Style Scalpel: A Free Forensic Stylometric AI-Text Analysis System

[The LINGUIST List]

LINGUIST List: Vol-37-1861. Thu May 21 2026. ISSN: 1069 - 4875.

Subject: 37.1861, Software: Style Scalpel: A Free Forensic Stylometric AI-Text Analysis System

Moderator: Steven Moran (linguist at linguistlist.org)
Managing Editor: Valeriia Vyshnevetska
Team: Helen Aristar-Dry, Mara Baccaro, Daniel Swanson
Jobs: jobs at linguistlist.org | Conferences: callconf at linguistlist.org | Pubs: pubs at linguistlist.org

Homepage: http://linguistlist.org

Editor for this issue: Daniel Swanson <daniel at linguistlist.org>

================================================================


Date: 20-May-2026
From: Muhammad Ismail [m0333ism at gmail.com]
Subject: Style Scalpel: A Free Forensic Stylometric AI-Text Analysis System


I would like to share Style Scalpel, a free forensic stylometric
AI-text analysis system developed from my research in computational
and forensic linguistics.
Style Scalpel is designed for exploratory comparison of human-written
and AI-generated texts using interpretable stylometric features. The
system focuses on transparent linguistic evidence rather than
black-box detector output.
The project currently includes:
- a live web interface
- a Windows desktop release
- GitHub documentation
- an OSF archive/DOI
- interactive feature-visualization maps for 132 stylometric features
Live system:
https://stylescalpel.com
GitHub repository:
https://github.com/m0333ism-dev/Style-Scalpel
Windows release:
https://github.com/m0333ism-dev/Style-Scalpel/releases/tag/v1.3
Feature visualization maps:
https://m0333ism-dev.github.io/Features-Graph-Map/
OSF archive / DOI:
https://doi.org/10.17605/OSF.IO/2D39J
The feature maps visualize normalized stylometric profiles for
human-written and AI-generated samples. They are intended to support
interpretability and comparison across feature groups, not to serve as
standalone classification evidence.
Style Scalpel should be treated as an analytical aid for research and
educational use. It should not be used as the only evidence for
accusing a writer of using AI. Its output should be interpreted
cautiously and in context, especially in academic integrity or
forensic-style settings.
I would welcome feedback from researchers working on corpora,
stylometry, authorship analysis, AI-generated text detection,
computational linguistics, forensic linguistics, or explainable NLP.

Linguistic Field(s): Applied Linguistics
                     Computational Linguistics
                     Forensic Linguistics
                     Text/Corpus Linguistics

Subject Language(s): English (eng)




------------------------------------------------------------------------------

********************** LINGUIST List Support ***********************
Please consider donating to the Linguist List, a U.S. 501(c)(3) not for profit organization:

https://www.paypal.com/donate/?hosted_button_id=87C2AXTVC4PP8

LINGUIST List is supported by the following publishers:

Bloomsbury Publishing http://www.bloomsbury.com/uk/

Cambridge University Press http://www.cambridge.org/linguistics

Cascadilla Press http://www.cascadilla.com/

De Gruyter Brill https://www.degruyterbrill.com/?changeLang=en

Edinburgh University Press http://www.edinburghuniversitypress.com

European Language Resources Association (ELRA) http://www.elra.info

John Benjamins http://www.benjamins.com/

Language Science Press http://langsci-press.org

Lincom GmbH https://lincom-shop.eu/

MDPI Languages https://www.mdpi.com/journal/languages

MIT Press http://mitpress.mit.edu/

Multilingual Matters http://www.multilingual-matters.com/

Narr Francke Attempto Verlag GmbH + Co. KG http://www.narr.de/

Netherlands Graduate School of Linguistics / Landelijke (LOT) http://www.lotpublications.nl/

Peter Lang AG http://www.peterlang.com

SIL International Publications http://www.sil.org/resources/publications


----------------------------------------------------------
LINGUIST List: Vol-37-1861
----------------------------------------------------------