@inproceedings{adam-etal-2026-team-hausanlp,
title = "Team {H}ausa{NLP} at {S}em{E}val-2026 Task 9: Tackling Class Imbalance in Low-Resource {H}ausa Polarization Detection",
author = "Adam, Faisal and
Aji, Sani and
Aliyu, Lukman and
Abubakar, Abdulhamid",
editor = "Kochmar, Ekaterina and
Ghosh, Debanjan and
North, Kai and
Komachi, Mamoru",
booktitle = "Proceedings of the 20th {I}nternational {W}orkshop on {S}emantic {E}valuation (2026)",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.semeval-1.8/",
pages = "54--58",
ISBN = "979-8-89176-414-9",
abstract = "This paper describes our submission toSemEval-2026 Task 9, Subtask 2 (Hausa). Thetask involves identifying specific categories ofpolarization (Political, Religious, Ethnic, etc.)in Hausa social media comments. The datasetpresented significant challenges, primarily extreme class imbalance and the low-resourcenature of the language. Our system uses a pretrained multilingual transformer (Afro-XLMRLarge) fine-tuned with Weighted Binary CrossEntropy loss and dynamic undersampling (1:3ratio) to mitigate the scarcity of polarized examples. On the official test set, our systemachieved an official Macro-F1 score of 0.2346and a Micro-F1 score of 0.2581. Our model isrecall-oriented (Micro-Recall: 0.6166), demonstrating strong capability in detecting polarization, though precision remains a challenge(0.1632). We achieved our best per-class performance in the Political domain (F1: 0.48)."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="adam-etal-2026-team-hausanlp">
<titleInfo>
<title>Team HausaNLP at SemEval-2026 Task 9: Tackling Class Imbalance in Low-Resource Hausa Polarization Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Faisal</namePart>
<namePart type="family">Adam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sani</namePart>
<namePart type="family">Aji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lukman</namePart>
<namePart type="family">Aliyu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdulhamid</namePart>
<namePart type="family">Abubakar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th International Workshop on Semantic Evaluation (2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Kochmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debanjan</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">North</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mamoru</namePart>
<namePart type="family">Komachi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-414-9</identifier>
</relatedItem>
<abstract>This paper describes our submission toSemEval-2026 Task 9, Subtask 2 (Hausa). Thetask involves identifying specific categories ofpolarization (Political, Religious, Ethnic, etc.)in Hausa social media comments. The datasetpresented significant challenges, primarily extreme class imbalance and the low-resourcenature of the language. Our system uses a pretrained multilingual transformer (Afro-XLMRLarge) fine-tuned with Weighted Binary CrossEntropy loss and dynamic undersampling (1:3ratio) to mitigate the scarcity of polarized examples. On the official test set, our systemachieved an official Macro-F1 score of 0.2346and a Micro-F1 score of 0.2581. Our model isrecall-oriented (Micro-Recall: 0.6166), demonstrating strong capability in detecting polarization, though precision remains a challenge(0.1632). We achieved our best per-class performance in the Political domain (F1: 0.48).</abstract>
<identifier type="citekey">adam-etal-2026-team-hausanlp</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.8/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>54</start>
<end>58</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Team HausaNLP at SemEval-2026 Task 9: Tackling Class Imbalance in Low-Resource Hausa Polarization Detection
%A Adam, Faisal
%A Aji, Sani
%A Aliyu, Lukman
%A Abubakar, Abdulhamid
%Y Kochmar, Ekaterina
%Y Ghosh, Debanjan
%Y North, Kai
%Y Komachi, Mamoru
%S Proceedings of the 20th International Workshop on Semantic Evaluation (2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-414-9
%F adam-etal-2026-team-hausanlp
%X This paper describes our submission toSemEval-2026 Task 9, Subtask 2 (Hausa). Thetask involves identifying specific categories ofpolarization (Political, Religious, Ethnic, etc.)in Hausa social media comments. The datasetpresented significant challenges, primarily extreme class imbalance and the low-resourcenature of the language. Our system uses a pretrained multilingual transformer (Afro-XLMRLarge) fine-tuned with Weighted Binary CrossEntropy loss and dynamic undersampling (1:3ratio) to mitigate the scarcity of polarized examples. On the official test set, our systemachieved an official Macro-F1 score of 0.2346and a Micro-F1 score of 0.2581. Our model isrecall-oriented (Micro-Recall: 0.6166), demonstrating strong capability in detecting polarization, though precision remains a challenge(0.1632). We achieved our best per-class performance in the Political domain (F1: 0.48).
%U https://aclanthology.org/2026.semeval-1.8/
%P 54-58
Markdown (Informal)
[Team HausaNLP at SemEval-2026 Task 9: Tackling Class Imbalance in Low-Resource Hausa Polarization Detection](https://aclanthology.org/2026.semeval-1.8/) (Adam et al., SemEval 2026)
ACL