@inproceedings{naseem-etal-2026-polar,
    title = "{POLAR}: A Benchmark for Multilingual, Multicultural, and Multi-Event Online Polarization",
    author = "Naseem, Usman  and
      Geislinger, Robert  and
      Ren, Juan  and
      Kohail, Sarah  and
      Veliz, Rudy Alexandro Garrido  and
      Sahil, P Sam  and
      Zhang, Yiran  and
      Abdulmumin, Idris  and
      Stranisci, Marco Antonio  and
      Alacam, {\textbackslash}{''}Ozge  and
      Acarturk, Cengiz  and
      Jabr, Aisha  and
      Anwar, Saba  and
      Ayele, Abinew Ali  and
      Frenda, Simona  and
      Cignarella, Alessandra Teresa  and
      Tutubalina, Elena  and
      Rogov, Oleg  and
      Htet, Aung Kyaw  and
      Wang, Xintong  and
      Thapa, Surendrabikram  and
      Rauniyar, Kritesh  and
      Chakraborty, Tanmoy  and
      Zeeshan, MD Arfeen  and
      Kodati, Dheeraj  and
      Keerthi, Satya  and
      Moradizeyveh, Sahar  and
      Alam, Firoj  and
      Hasan, Md Arid  and
      Ahmed, Syed Ishtiaque  and
      Thu, Ye Kyaw  and
      Parida, Shantipriya  and
      Qazi, Ihsan Ayyub  and
      Wanzare, Lilian Diana Awuor  and
      Onyango, Nelson Odhiambo  and
      Siro, Clemencia  and
      Kimani, Jane Wanjiru  and
      Ahmad, Ibrahim Said  and
      Ali, Adem Chanie  and
      Semmann, Martin  and
      Biemann, Chris  and
      Muhammad, Shamsuddeen Hassan  and
      Yimam, Seid Muhie",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1433/",
    pages = "28699--28720",
    ISBN = "979-8-89176-395-1",
    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. Results show that while most models perform well on 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 underscore 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."
}