@inproceedings{ben-arbia-etal-2026-comparative,
title = "Comparative Study of Machine Learning and Transformer-Based Approaches for {A}rabic Politeness Detection at {A}dab{E}val 2026",
author = "Ben Arbia, Mariem and
Ben Amor, Ghada and
Trigui, Omar",
editor = "Al-Khalifa, Hend and
El-Haj, Mo and
Ezzini, Saad",
booktitle = "The 7th Workshop on Open-Source {A}rabic Corpora and Processing Tools ({OSACT}7) with 5 Shared Tasks",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.osact-1.21/",
doi = "10.63317/2vdvaesuziyj",
pages = "179--184",
abstract = "This paper describes our system submitted to the OSACT7 AdabEval shared task on Arabic politeness detection (TaskA). The task requires classifying Arabic texts into three categories: Polite, Impolite, and Neutral. We systematically explore multiple approaches, progressing from classical machine learning baselines using pre-trained embeddings to fine-tuned transformer models. Our best system leverages MARBERT, a transformer model pre-trained on one billion Arabic tweets, fine-tuned with Focal Loss to handle the significant class imbalance present in the dataset (70{\%} Neutral). We additionally experiment with hybrid approaches combining fine-tuned embeddings with gradient-boosted classifiers and ensemble methods. Our best single model achieves a macro F1 score of 0.84 and an accuracy of 0.90 on the validation set, substantially outperforming classical ML baselines (F1 = 0.42)."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ben-arbia-etal-2026-comparative">
<titleInfo>
<title>Comparative Study of Machine Learning and Transformer-Based Approaches for Arabic Politeness Detection at AdabEval 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mariem</namePart>
<namePart type="family">Ben Arbia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ghada</namePart>
<namePart type="family">Ben Amor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omar</namePart>
<namePart type="family">Trigui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>The 7th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT7) with 5 Shared Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mo</namePart>
<namePart type="family">El-Haj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saad</namePart>
<namePart type="family">Ezzini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes our system submitted to the OSACT7 AdabEval shared task on Arabic politeness detection (TaskA). The task requires classifying Arabic texts into three categories: Polite, Impolite, and Neutral. We systematically explore multiple approaches, progressing from classical machine learning baselines using pre-trained embeddings to fine-tuned transformer models. Our best system leverages MARBERT, a transformer model pre-trained on one billion Arabic tweets, fine-tuned with Focal Loss to handle the significant class imbalance present in the dataset (70% Neutral). We additionally experiment with hybrid approaches combining fine-tuned embeddings with gradient-boosted classifiers and ensemble methods. Our best single model achieves a macro F1 score of 0.84 and an accuracy of 0.90 on the validation set, substantially outperforming classical ML baselines (F1 = 0.42).</abstract>
<identifier type="citekey">ben-arbia-etal-2026-comparative</identifier>
<identifier type="doi">10.63317/2vdvaesuziyj</identifier>
<location>
<url>https://aclanthology.org/2026.osact-1.21/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>179</start>
<end>184</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Comparative Study of Machine Learning and Transformer-Based Approaches for Arabic Politeness Detection at AdabEval 2026
%A Ben Arbia, Mariem
%A Ben Amor, Ghada
%A Trigui, Omar
%Y Al-Khalifa, Hend
%Y El-Haj, Mo
%Y Ezzini, Saad
%S The 7th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT7) with 5 Shared Tasks
%D 2026
%8 May
%I Association for Computational Linguistics
%C Palma, Mallorca (Spain)
%F ben-arbia-etal-2026-comparative
%X This paper describes our system submitted to the OSACT7 AdabEval shared task on Arabic politeness detection (TaskA). The task requires classifying Arabic texts into three categories: Polite, Impolite, and Neutral. We systematically explore multiple approaches, progressing from classical machine learning baselines using pre-trained embeddings to fine-tuned transformer models. Our best system leverages MARBERT, a transformer model pre-trained on one billion Arabic tweets, fine-tuned with Focal Loss to handle the significant class imbalance present in the dataset (70% Neutral). We additionally experiment with hybrid approaches combining fine-tuned embeddings with gradient-boosted classifiers and ensemble methods. Our best single model achieves a macro F1 score of 0.84 and an accuracy of 0.90 on the validation set, substantially outperforming classical ML baselines (F1 = 0.42).
%R 10.63317/2vdvaesuziyj
%U https://aclanthology.org/2026.osact-1.21/
%U https://doi.org/10.63317/2vdvaesuziyj
%P 179-184
Markdown (Informal)
[Comparative Study of Machine Learning and Transformer-Based Approaches for Arabic Politeness Detection at AdabEval 2026](https://aclanthology.org/2026.osact-1.21/) (Ben Arbia et al., OSACT 2026)
ACL