Search papers, labs, and topics across Lattice.
The SemEval-2026 Task 9 shared task addressed the challenge of detecting online polarization across 22 languages, using a dataset of 110K multi-labeled instances annotated for presence, type, and manifestation of polarization. The task involved three sub-tasks focused on different aspects of polarization detection, attracting significant participation with over 1,000 participants and 67 final submissions. Analysis of the submitted systems revealed common approaches and effective methods for different subtasks and languages, providing valuable insights into multilingual polarization detection.
A large-scale, multilingual dataset for online polarization detection is now available, offering a benchmark for future research in this critical area.
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.
