@inproceedings{andriyanova-almaamary-2026-moska,
title = "{MOSKA}-{NLP} at {A}dab{E}val 2026: Feature-Enriched Ensembling for {A}rabic Politeness Detection",
author = "Andriyanova-Almaamary, Nina A.",
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-1.19/",
doi = "10.63317/56vfmbyh3fsv",
pages = "165--173",
abstract = "In this paper, we present our system for subtask A of the AdabEval 2026 shared task, which focuses on classifying Arabic text into Polite, Neutral, and Impolite categories. Politeness detection is challenging because it cannot be inferred from lexical meaning alone. This is prominent in Arabic language, where politeness is often conveyed through formulaic expressions, stylistic cues, and dialectal variations. Our approach follows a three-stage strategy. First, we evaluate five Arabic sentence embedding models based on different pretrained encoders to identify a strong representation backbone. Second, we enrich sentence embeddings with explicit lexical, surface-level, and auxiliary signals derived from external models, including dialect, intent, and sarcasm classifiers. Third, we combine predictions from independently trained models, using weighted probability-level ensembling with class-specific decision thresholds to address class imbalance. Experimental results show that feature-enriched representations consistently outperform embedding-only baselines, with additional gains obtained from calibrated ensembling. The proposed system achieves a macro-F1 score of 0.87 and an accuracy of 93{\%} on the official AdabEval 2026 evaluation for subtask A."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="andriyanova-almaamary-2026-moska">
<titleInfo>
<title>MOSKA-NLP at AdabEval 2026: Feature-Enriched Ensembling for Arabic Politeness Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nina</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Andriyanova-Almaamary</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>In this paper, we present our system for subtask A of the AdabEval 2026 shared task, which focuses on classifying Arabic text into Polite, Neutral, and Impolite categories. Politeness detection is challenging because it cannot be inferred from lexical meaning alone. This is prominent in Arabic language, where politeness is often conveyed through formulaic expressions, stylistic cues, and dialectal variations. Our approach follows a three-stage strategy. First, we evaluate five Arabic sentence embedding models based on different pretrained encoders to identify a strong representation backbone. Second, we enrich sentence embeddings with explicit lexical, surface-level, and auxiliary signals derived from external models, including dialect, intent, and sarcasm classifiers. Third, we combine predictions from independently trained models, using weighted probability-level ensembling with class-specific decision thresholds to address class imbalance. Experimental results show that feature-enriched representations consistently outperform embedding-only baselines, with additional gains obtained from calibrated ensembling. The proposed system achieves a macro-F1 score of 0.87 and an accuracy of 93% on the official AdabEval 2026 evaluation for subtask A.</abstract>
<identifier type="citekey">andriyanova-almaamary-2026-moska</identifier>
<identifier type="doi">10.63317/56vfmbyh3fsv</identifier>
<location>
<url>https://aclanthology.org/2026.osact-1.19/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>165</start>
<end>173</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MOSKA-NLP at AdabEval 2026: Feature-Enriched Ensembling for Arabic Politeness Detection
%A Andriyanova-Almaamary, Nina A.
%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 andriyanova-almaamary-2026-moska
%X In this paper, we present our system for subtask A of the AdabEval 2026 shared task, which focuses on classifying Arabic text into Polite, Neutral, and Impolite categories. Politeness detection is challenging because it cannot be inferred from lexical meaning alone. This is prominent in Arabic language, where politeness is often conveyed through formulaic expressions, stylistic cues, and dialectal variations. Our approach follows a three-stage strategy. First, we evaluate five Arabic sentence embedding models based on different pretrained encoders to identify a strong representation backbone. Second, we enrich sentence embeddings with explicit lexical, surface-level, and auxiliary signals derived from external models, including dialect, intent, and sarcasm classifiers. Third, we combine predictions from independently trained models, using weighted probability-level ensembling with class-specific decision thresholds to address class imbalance. Experimental results show that feature-enriched representations consistently outperform embedding-only baselines, with additional gains obtained from calibrated ensembling. The proposed system achieves a macro-F1 score of 0.87 and an accuracy of 93% on the official AdabEval 2026 evaluation for subtask A.
%R 10.63317/56vfmbyh3fsv
%U https://aclanthology.org/2026.osact-1.19/
%U https://doi.org/10.63317/56vfmbyh3fsv
%P 165-173
Markdown (Informal)
[MOSKA-NLP at AdabEval 2026: Feature-Enriched Ensembling for Arabic Politeness Detection](https://aclanthology.org/2026.osact-1.19/) (Andriyanova-Almaamary, OSACT 2026)
ACL