arXivDaily arXiv每日学术速递 周一至周五更新
​通知:联邦节假日调休:哥伦布日 / 原住民日(Columbus Day / Indigenous Peoples' Day),今日(13日)无更新。
arXiv 2606.12068cs.CL

StanceNakba 共享任务:公共话语中基于行动者和主题的立场检测

StanceNakba Shared Task: Actor and Topic-Aware Stance Detection in Public Discourse

Northwestern University in Qatar(卡塔尔西北大学);Hamad Bin Khalifa University(哈利法大学)

Kholoud K. Aldous, Md Rafiul Biswas, Mabrouka Bessghaier, Shimaa Ibrahim, Kais Attia, Wajdi Zaghouani

AI总结:

提出 StanceNakba 2026 共享任务,通过两个子任务(行动者级和跨主题立场检测)利用微调 Transformer 模型(如 MARBERT、AraBERT)在巴以冲突相关社交媒体数据上实现高 Macro F1 分数。

摘要:

我们提出 StanceNakba 2026,这是一个关于巴以冲突相关极化社交媒体话语中立场检测的共享任务,作为 LREC-COLING 2026 上 Nakba-NLP 2026 的一部分组织。该任务引入两个子任务:子任务 A(行动者级立场检测),将英语社交媒体帖子分类为亲巴勒斯坦、亲以色列或中立;子任务 B(跨主题立场检测),识别阿拉伯语帖子中关于两个冲突相关主题(与以色列正常化以及约旦难民存在)的赞成、反对或中立立场。该任务基于一个包含 2,606 条社交媒体帖子的标注数据集。共有 7 个团队参加了子任务 A,6 个团队参加了子任务 B。参与系统主要微调了阿拉伯语和多语言基于 Transformer 的模型,包括 MARBERT、AraBERT 和 DeBERTa-v3 变体,多个团队采用了交叉验证、集成方法和主题条件架构。表现最佳的系统在子任务 A 上达到了 0.9620 的 Macro F1,在子任务 B 上达到了 0.8724,表明基于 Transformer 的方法对于冲突领域立场检测非常有效,同时突显了跨主题泛化和中立类别预测方面的持续挑战。

英文摘要:

We present StanceNakba 2026, a shared task on stance detection in polarized social media discourse related to the Palestinian-Israeli conflict, organized as part of Nakba-NLP 2026 at LREC-COLING 2026. The task introduces two subtasks: Subtask A (Actor-Level Stance Detection), which classifies English social media posts as Pro-Palestine, Pro-Israel, or Neutral; and Subtask B (Cross-Topic Stance Detection), which identifies Favor, Against, or Neither stances in Arabic posts toward two conflict-related topics, normalization with Israel and refugee presence in Jordan. The task is grounded in an annotated dataset of 2,606 social media posts. A total of 7 teams participated in Subtask A and 6 teams in Subtask B. Participating systems primarily fine-tuned Arabic and multilingual transformer-based models, including MARBERT, AraBERT, and DeBERTa-v3 variants, with several teams employing cross-validation, ensemble methods, and topic-conditioned architectures. The best-performing systems achieved a Macro F1 of 0.9620 on Subtask A and 0.8724 on Subtask B, demonstrating that transformer-based approaches are highly effective for conflict-domain stance detection while highlighting persistent challenges in cross-topic generalization and neutral class prediction.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑