Linguistic Features Embedded in Arabic Transformers: A Feature Ablation Study for E-Commerce Deepfake Detection

Traditionally, Arabic natural language processing pipelines apply aggressive preprocessing, including removing punctuation, normalizing characters, and eliminating emojis, based on the assumption that cleaner inputs yield better model performance. This study investigates the linguistic features embedded in Arabic transformer models for detecting synthetic product listings in e-commerce environments. We conducted a systematic ablation study to evaluate the impact of removing individual linguistic feature categories on the classification performance of four Arabic transformer models. Our results show that preprocessing Arabic e-commerce text is not simply a matter of removing noise: the punctuation functions as a consistent structural signal across all architectures, numeric characters and English text behave as model-dependent specification-carrying signals, and emojis have no measurable effect across the models. These findings provide a practical framework for understanding the linguistic features embedded in Arabic transformers for e-commerce deepfake detection and suggest that preprocessing pipelines should preserve domain-relevant structures, rather than aggressively applying uniform cleaning.

Authors

Institutions

Publication Details

Published
2026-11-16
DOI
https://doi.org/10.64589/juri/231620
Primary Topic
Spam and Phishing Detection
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Linguistic Features Embedded in Arabic Transformers: A Feature Ablation Study for E-Commerce Deepfake Detection

Tarek Helmy, Amal Sunba, Rashed Essam Jafry
3 links
Spam and Phishing Detection
article

Linguistic Features Embedded in Arabic Transformers: A Feature Ablation Study for E-Commerce Deepfake Detection

Tarek Helmy, Amal Sunba, Rashed Essam Jafry
article en

Abstract

Traditionally, Arabic natural language processing pipelines apply aggressive preprocessing, including removing punctuation, normalizing characters, and eliminating emojis, based on the assumption that cleaner inputs yield better model performance. This study investigates the linguistic features embedded in Arabic transformer models for detecting synthetic product listings in e-commerce environments. We conducted a systematic ablation study to evaluate the impact of removing individual linguistic feature categories on the classification performance of four Arabic transformer models. Our results show that preprocessing Arabic e-commerce text is not simply a matter of removing noise: the punctuation functions as a consistent structural signal across all architectures, numeric characters and English text behave as model-dependent specification-carrying signals, and emojis have no measurable effect across the models. These findings provide a practical framework for understanding the linguistic features embedded in Arabic transformers for e-commerce deepfake detection and suggest that preprocessing pipelines should preserve domain-relevant structures, rather than aggressively applying uniform cleaning.

Vol. 2(3B)
Princess Nourah bint Abdulrahman University (SA), King Fahd University of Petroleum and Minerals (SA)
King Fahd University of Petroleum and Minerals
Spam and Phishing Detection
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon