SemEval-2026 任务 9：检测多语言、多文化与多事件在线极化
计算与语言
2026-04-09 v1
摘要
我们介绍 SemEval-2026 任务 9，这是一个涵盖 22 种语言、包含 11 万多余注释实例的在线极化检测共享任务。每个数据实例都以极化的存在、极化类型和极化表现形式进行多标签标注。参赛者被要求在三个子任务中预测标签：(1) 检测极化的存在，(2) 识别极化类型，(3) 识别极化表现形式。该三个任务吸引了来自全球 1000 多名参赛者，超过 1 万 份提交。我们收到了 67 支团队提交的最终结果和 73 篇系统描述论文。我们报告基线结果，分析最佳系统的性能，突出不同子任务和语言中最常见的方法和最有效的方法。该任务的数据集已公开提供。
引用
@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}
}