StanceNakba 2026 Shared Task: Stance Detection in Palestinian-Israeli Conflict Discourse
Researchers organized StanceNakba 2026, a shared task on detecting stance in social media posts about the Palestinian-Israeli conflict, with two subtasks covering English and Arabic posts. The task involved 7 teams on English stance classification (Pro-Palestine, Pro-Israel, Neutral) and 6 teams on Arabic cross-topic stance detection, using a dataset of 2,606 annotated posts. The results demonstrate that transformer-based models are effective for conflict-domain stance detection, though challenges remain in cross-topic generalization and neutral class prediction.
StanceNakba 2026 is a shared task presented at LREC-COLING 2026 focused on stance detection in polarized social media discourse related to the Palestinian-Israeli conflict. Subtask A requires classifying English social media posts into Pro-Palestine, Pro-Israel, or Neutral categories, while Subtask B involves identifying Favor, Against, or Neither stances in Arabic posts toward two specific topics: normalization with Israel and refugee presence in Jordan. The task is grounded in an annotated dataset of 2,606 social media posts. Participating teams (7 in Subtask A, 6 in Subtask B) primarily employed fine-tuned transformer-based models including MARBERT, AraBERT, and DeBERTa-v3 variants, with several using cross-validation, ensemble methods, and topic-conditioned architectures. The best-performing systems achieved a Macro F1 score of 0.9620 on Subtask A and 0.8724 on Subtask B, demonstrating the effectiveness of transformer-based approaches for stance detection in conflict-related discourse while revealing persistent challenges in cross-topic generalization and neutral class prediction.
What different sources said
- arXiv cs.CLCenter
StanceNakba Shared Task: Actor and Topic-Aware Stance Detection in Public Discourse
Related
Genetic Drift, Not Selection, Drives Rapid Feather Color Evolution in Island Bird Radiation
A new study of an island bird radiation found that rapid evolution of feather coloration is driven primarily by genetic drift in small populations rather than sexual or ecological selection. The research integrated whole-genome data with detailed plumage measurements across complete species sampling to test whether signaling trait evolution correlates with speciation rates. The findings suggest that neutral demographic processes play a central role in generating phenotypic diversity during island radiations, challenging assumptions about the mechanisms driving rapid evolution.
New AI Model Improves Prediction of Therapeutic Peptide Function from Protein Sequences
Researchers developed a lightweight CNN classifier that predicts whether peptide sequences have therapeutic properties, trained on a database of 54,655 peptides across 48 functional categories. The model uses a novel negative sampling strategy to reduce false positive rates from over 60% in previous approaches to 2.1%. This advancement could accelerate drug discovery by enabling faster computational screening of peptide candidates before expensive experimental testing.
Study Shows Different Metabolic Stress Models Produce Distinct Effects on Human Neuronal Networks
Researchers tested three common in vitro metabolic stress models on human-derived neuronal networks and found each produced different patterns of neuronal activity and cell damage. The models tested were hypoxia alone, oxygen-glucose deprivation (OGD), and hypoxia combined with glutamate exposure. The findings suggest that choice of experimental model significantly affects results and that combining electrophysiological and structural analyses is important for accurately assessing metabolic stress in stroke research.