用加权损失和阈值调优提升多语言极化检测效果
Multilingual Polarization Detection Using Transformer-Based Models with Class Weighting and Threshold Tuning
- 针对标签不平衡问题，采用类别加权损失函数
- 在英、斯瓦希里语上实现最高0.791的宏F1分数
- 适合关注跨文化极化分析的研究者使用
本文描述了我们参加SemEval-2026任务9的提交方案，该任务旨在检测多语言、多文化、多事件的在线极化现象。我们完成了三个子任务：二分类极化检测、极化类型分类和英文与斯瓦希里语的极化表现形式识别。方法上，采用RoBERTa-base（英文）和AfroXLMR-base（斯瓦希里语）等Transformer模型，结合类别加权损失函数缓解严重标签不平衡，并通过每个标签的阈值调优优化多标签分类。在测试集上，英、斯语在子任务1的宏F1分别为0.7901和0.7910，子任务2为0.4615和0.4808，子任务3为0.4791和0.5830，在排行榜中表现优异，验证了方法在处理不平衡多标签极化检测中的有效性。错误分析显示模型在去人性化识别和共情缺失检测上仍存在困难。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。