POLAR: A Benchmark for Multilingual, Multicultural, and Multi-Event Online Polarization
Abstract
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.
Cite
@article{arxiv.2505.20624,
title = {POLAR: A Benchmark for Multilingual, Multicultural, and Multi-Event Online Polarization},
author = {Usman Naseem and Robert Geislinger and Juan Ren and Sarah Kohail and Rudy Garrido Veliz and P Sam Sahil and Yiran Zhang and Marco Antonio Stranisci and Idris Abdulmumin and Özge Alacam and Cengiz Acartürk and Aisha Jabr and Saba Anwar and Abinew Ali Ayele and Simona Frenda and Alessandra Teresa Cignarella and Elena Tutubalina and Oleg Rogov and Aung Kyaw Htet and Xintong Wang and Surendrabikram Thapa and Kritesh Rauniyar and Tanmoy Chakraborty and Arfeen Zeeshan and Dheeraj Kodati and Satya Keerthi and Sahar Moradizeyveh and Firoj Alam and Arid Hasan and Syed Ishtiaque Ahmed and Ye Kyaw Thu and Shantipriya Parida and Ihsan Ayyub Qazi and Lilian Wanzare and Nelson Odhiambo Onyango and Clemencia Siro and Jane Wanjiru Kimani and Ibrahim Said Ahmad and Adem Chanie Ali and Martin Semmann and Chris Biemann and Shamsuddeen Hassan Muhammad and Seid Muhie Yimam},
journal= {arXiv preprint arXiv:2505.20624},
year = {2026}
}
Comments
Preprint