Multilingual Polarization Detection Using Transformer-Based Models with Class Weighting and Threshold Tuning

Researchers submitted a system to SemEval-2026 Task 9 for detecting multilingual online polarization using transformer-based models with class weighting and threshold tuning. Their approach achieved competitive F1 macro scores on English and Swahili test sets, though error analysis showed struggles with dehumanization detection and lack of empathy.

arXiv:2606.30857v1 Announce Type: new Abstract: This paper describes our submission to SemEval-2026 Task 9 on detecting multilingual, multicultural, and multievent online polarization. We address all three subtasks: binary polarization detection, polarization type classification, and manifestation identification for English and Swahili. Our approach leverages transformer-based models RoBERTa-base for English, AfroXLMR-base for Swahili with class-weighted loss functions to address severe label imbalance and per-label threshold tuning to optimize multi-label classification. On the test set, we achieve F1 macro scores of 0.7901 English and 0.7910 Swahili for Subtask 1, 0.4615 English and 0.4808 Swahili for Subtask 2 and 0.4791 English and 0.5830 Swahili for Subtask 3, which give competitive performance on the leaderboard, demonstrating the effectiveness of our methods for handling imbalanced multi-label polarization detection. Our error analysis reveals that models struggle with dehumanization detection and lack of empathy.