# POLAR: A Benchmark for Multilingual, Multicultural, and Multi-Event Online Polarization

arXiv: https://arxiv.org/abs/2505.20624 · HTML: https://mlsanity.com/paper/2505.20624/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 38 references that are in the map.
- First posted on arXiv 27 May 2025.

## Builds on (most cited first, 10 of 10)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [Language-agnostic BERT Sentence Embedding](https://mlsanity.com/paper/2007.01852/) (2020)
- [HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection](https://mlsanity.com/paper/2012.10289/) (2020)
- [InfoXLM: An Information-Theoretic Framework for Cross-Lingual Language Model Pre-Training](https://mlsanity.com/paper/2007.07834/) (2020)
- [Rethinking embedding coupling in pre-trained language models](https://mlsanity.com/paper/2010.12821/) (2020)
- [POTATO: The Portable Text Annotation Tool](https://mlsanity.com/paper/2212.08620/) (2022)
- [Quantifying social organization and political polarization in online platforms](https://mlsanity.com/paper/2010.00590/) (2020)
- [SemEval-2024 Task 1: Semantic Textual Relatedness for African and Asian Languages](https://mlsanity.com/paper/2403.18933/) (2024)

## Built on by (most cited first, 4 of 4)

- [SemEval-2026 Task 9: Detecting Multilingual, Multicultural and Multievent Online Polarization](https://mlsanity.com/paper/2604.06817/) (2026)
- [MKJ at SemEval-2026 Task 9: A Comparative Study of Generalist, Specialist, and Ensemble Strategies for Multilingual Polarization](https://mlsanity.com/paper/2604.21370/) (2026)
- [YEZE at SemEval-2026 Task 9: Detecting Multilingual, Multicultural and Multievent Online Polarization via Heterogeneous Ensembling](https://mlsanity.com/paper/2605.06231/) (2026)
- [Polarization Detection: A Hybrid Approach with AfroXLMR-Social and DeBERTa for Low- and High-Resource Settings](https://mlsanity.com/paper/2607.10312/) (2026)

## Abstract (arXiv)

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.