SemEval-2026 Task 9: Detecting Multilingual, Multicultural and Multievent Online Polarization
Abstract
We present SemEval-2026 Task 9, a shared task on online polarization detection, covering 22 languages and comprising over 110K annotated instances. Each data instance is multi-labeled with the presence of polarization, polarization type, and polarization manifestation. Participants were asked to predict labels in three sub-tasks: (1) detecting the presence of polarization, (2) identifying the type of polarization, and (3) recognizing the polarization manifestation. The three tasks attracted over 1,000 participants worldwide and more than 10k submission on Codabench. We received final submissions from 67 teams and 73 system description papers. We report the baseline results and analyze the performance of the best-performing systems, highlighting the most common approaches and the most effective methods across different subtasks and languages. The dataset of this task is publicly available.
Cite
@article{arxiv.2604.06817,
title = {SemEval-2026 Task 9: Detecting Multilingual, Multicultural and Multievent 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 Alaçam and Cengiz Acartürk and Aisha Jabr and Saba Anwar and Abinew Ali Ayele and Elena Tutubalina and Aung Kyaw Htet and Xintong Wang and Surendrabikram Thapa and Tanmoy Chakraborty and Dheeraj Kodati and Sahar Moradizeyveh and Firoj Alam and Ye Kyaw Thu and Shantipriya Parida and Ihsan Ayyub Qazi and Lilian Wanzare and Nelson Odhiambo Onyango and Clemencia Siro 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:2604.06817},
year = {2026}
}