arXiv：cs.CL· Rasha Albalawi, Nuha Albadi, Hamzah Luqman, Maram Kurdi, Saad Ezzini, Asma Yamani, Ahmed Ashraf·· 4 小时前AI 评分29
Mawqif-XT：面向跨目标立场检测的阿拉伯语基准数据集
Mawqif-XT: An Arabic Benchmark Dataset for Cross-Target Stance Detection
AI 导读
Mawqif-XT 是一个包含 996 条人工标注阿拉伯语推文的跨目标立场检测基准数据集，覆盖 Women Driving、E-Cars 和 Trimester System 三个公开目标，每条推文按原 Mawqif 标注方案标注立场、情感和讽刺标签。
正文
Abstract:Publicly available Arabic datasets for target-specific stance detection remain limited, particularly for evaluating cross-target generalization. This paper presents the Mawqif-XT, consisting of 996 manually annotated Arabic tweets collected from three public targets: Women Driving, E-Cars, and Trimester System. Each tweet is annotated with stance, sentiment, and sarcasm labels following the original Mawqif annotation scheme. The released extension is intended as a held-out evaluation set for assessing model generalization to both semantically related and previously unseen targets, while the original Mawqif dataset is used for training and development. In addition, we establish baseline results using several Arabic and multilingual transformer models, as well as zero-shot large language models (LLMs), to facilitate reproducible evaluation. Together with the original Mawqif dataset, the Mawqif-v2 Extension provides a benchmark for evaluating cross-target generalization in Arabic stance detection.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2608.09539 [cs.CL] |
| (or arXiv:2608.09539v3 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2608.09539 arXiv-issued DOI via DataCite |
Submission history
From: Rasha Albalawi [view email]
[v1]
Mon, 10 Aug 2026 12:36:21 UTC (1,777 KB)
[v2]
Thu, 13 Aug 2026 15:13:49 UTC (1,777 KB)
[v3]
Fri, 2 Oct 2026 12:39:49 UTC (1,777 KB)
来源：arXiv：cs.CL · arxiv.org