DeepSemantics at SemEval-2026 Task 9: Label-Wise Optimization with Adaptive Focal Loss for Polarization Manifestation Identification

Résumé

In this paper, we present our system for SemEval-2026 Task 9, which focuses on the fine-grained identification of polarization manifestations in multilingual social media content.Our approach combines transformer-based encoders (RoBERTa-base for English and Afro-XLM-R-small for Hausa) within a One-vs-Rest (OvR) framework, complemented by controlled oversampling, Adaptive Focal Loss, and labelwise threshold optimization.To mitigate severe class imbalance and label sparsity, we adopt language-specific optimization strategies supported by pairwise χ 2 independence analysis.Our system achieves macro-F1 scores of 0.464 in English and 0.192 in Hausa on the official test sets, ranking 5 th in Hausa and 14 th in English on the official leaderboard.Our code is publicly available 1 .

Citer ce document

Accès au document

Texte intégral en lecture en ligne, réservé aux abonnés SPHAERO et aux membres de l'institution. Se connecter

Auteur(s)

Statistiques

Consultations : 1

Téléchargements : 0