Online polarization poses a growing challenge for democratic discourse, yet most computational social science research remains monolingual, culturally narrow, or event-specific. We introduce POLAR, a multilingual, multicultural, and multi-event dataset with over 110K instances in 22 languages drawn from diverse online platforms and real-world events. Polarization is annotated along three axes, namely detection, type, and manifestation, using a variety of annotation platforms adapted to each cultural context. We conduct two main experiments: (1) fine-tuning six pretrained small language models; and (2) evaluating a range of open and closed large language models in few-shot and zero-shot settings. The results show that, while most models perform well in binary polarization detection, they achieve substantially lower performance when predicting polarization types and manifestations. These findings highlight the complex, highly contextual nature of polarization and demonstrate the need for robust, adaptable approaches in NLP and computational social science. All resources will be released to support further research and effective mitigation of digital polarization globally.

翻译：在线极化对民主话语构成了日益严峻的挑战，然而大多数计算社会科学研究仍然是单语的、文化视野狭窄的或局限于特定事件的。我们提出了POLAR，这是一个多语言、多文化、多事件的数据集，包含来自不同在线平台和现实世界事件的超过11万个实例，涵盖22种语言。极化标注沿着三个维度进行，即检测、类型和表现形式，并针对每种文化背景采用了多种适应的标注平台。我们进行了两项主要实验：(1) 微调六个预训练的小型语言模型；(2) 在少样本和零样本设置下评估一系列开源和闭源的大型语言模型。结果表明，虽然大多数模型在二元极化检测上表现良好，但在预测极化类型和表现形式时，其性能显著降低。这些发现凸显了极化现象的复杂性和高度情境依赖性，并证明了在自然语言处理和计算社会科学领域需要开发鲁棒且适应性强的研究方法。所有资源将被公开，以支持全球范围内进一步的研究和有效缓解数字极化。