{"ID":5439492,"CreatedAt":"2026-07-01T01:17:58.482524686Z","UpdatedAt":"2026-07-02T19:37:48.020935119Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.30857","arxiv_id":"2606.30857","title":"Multilingual Polarization Detection Using Transformer-Based Models with Class Weighting and Threshold Tuning","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.","short_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 transf...","url_abs":"https://arxiv.org/abs/2606.30857","url_pdf":"https://arxiv.org/pdf/2606.30857v1","authors":"[\"Aaron Bundi Anampiu\"]","published":"2026-06-29T19:42:52Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Transformer\"]","has_code":false}