@inproceedings{anabtawi-2026-stylometric,
title = "A Stylometric and Statistical Pipeline for {U}rdu {AI}-Generated Text Classification",
author = "Anabtawi, saeed A.",
booktitle = "Proceedings of the 2nd Workshop on {NLP} for Languages Using {A}rabic Script",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.abjadnlp-1.58/",
pages = "472--475",
abstract = "The proliferation of Large Language Models (LLMs) has introduced significant challenges regarding algorithmic bias, privacy, and the authenticity of digital content. While detection mechanisms for English are maturing, low-resource languages like Urdu{---}spoken by over 100 million people{---}require dedicated research. In this paper, we present a technical framework for Urdu AI-generated text detection developed for the *ACL shared task. We propose a hybrid pipeline that combines TF-IDF Character N-grams with a custom stylometric feature extractor designed to capture unique Urdu linguistic markers, including repeated word ratios, punctuation density, and formal function markers. Using a Linear Support Vector Machine (SVM) optimized via Stochastic Gradient Descent (SGD), our system achieves a balanced accuracy and $F_1$-score of 87.80{\%} on a dataset of 6,800 records. Our results demonstrate that a computationally efficient, classical machine learning approach{---}prioritizing stylistic signals over heavy preprocessing{---}remains highly effective for distinguishing between human-written and AI-generated Urdu text."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="anabtawi-2026-stylometric">
<titleInfo>
<title>A Stylometric and Statistical Pipeline for Urdu AI-Generated Text Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">saeed</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Anabtawi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on NLP for Languages Using Arabic Script</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The proliferation of Large Language Models (LLMs) has introduced significant challenges regarding algorithmic bias, privacy, and the authenticity of digital content. While detection mechanisms for English are maturing, low-resource languages like Urdu—spoken by over 100 million people—require dedicated research. In this paper, we present a technical framework for Urdu AI-generated text detection developed for the *ACL shared task. We propose a hybrid pipeline that combines TF-IDF Character N-grams with a custom stylometric feature extractor designed to capture unique Urdu linguistic markers, including repeated word ratios, punctuation density, and formal function markers. Using a Linear Support Vector Machine (SVM) optimized via Stochastic Gradient Descent (SGD), our system achieves a balanced accuracy and F₁-score of 87.80% on a dataset of 6,800 records. Our results demonstrate that a computationally efficient, classical machine learning approach—prioritizing stylistic signals over heavy preprocessing—remains highly effective for distinguishing between human-written and AI-generated Urdu text.</abstract>
<identifier type="citekey">anabtawi-2026-stylometric</identifier>
<location>
<url>https://aclanthology.org/2026.abjadnlp-1.58/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>472</start>
<end>475</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Stylometric and Statistical Pipeline for Urdu AI-Generated Text Classification
%A Anabtawi, saeed A.
%S Proceedings of the 2nd Workshop on NLP for Languages Using Arabic Script
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%F anabtawi-2026-stylometric
%X The proliferation of Large Language Models (LLMs) has introduced significant challenges regarding algorithmic bias, privacy, and the authenticity of digital content. While detection mechanisms for English are maturing, low-resource languages like Urdu—spoken by over 100 million people—require dedicated research. In this paper, we present a technical framework for Urdu AI-generated text detection developed for the *ACL shared task. We propose a hybrid pipeline that combines TF-IDF Character N-grams with a custom stylometric feature extractor designed to capture unique Urdu linguistic markers, including repeated word ratios, punctuation density, and formal function markers. Using a Linear Support Vector Machine (SVM) optimized via Stochastic Gradient Descent (SGD), our system achieves a balanced accuracy and F₁-score of 87.80% on a dataset of 6,800 records. Our results demonstrate that a computationally efficient, classical machine learning approach—prioritizing stylistic signals over heavy preprocessing—remains highly effective for distinguishing between human-written and AI-generated Urdu text.
%U https://aclanthology.org/2026.abjadnlp-1.58/
%P 472-475
Markdown (Informal)
[A Stylometric and Statistical Pipeline for Urdu AI-Generated Text Classification](https://aclanthology.org/2026.abjadnlp-1.58/) (Anabtawi, AbjadNLP 2026)
ACL