Mawqif-v2: An Arabic Benchmark Dataset for Cross-Target Stance Detection
2026-08-10 • Computation and Language
Computation and Language
AI summaryⓘ
The authors created a new set of nearly 1,000 Arabic tweets called the Mawqif-v2 Extension, each labeled for stance, sentiment, and sarcasm about topics like Women Driving, E-Cars, and Trimester System. This new data is designed to test how well models trained on the original Mawqif dataset can understand opinions on new but related subjects. They also tested several Arabic and multilingual AI models to provide baseline results for others to compare against. Together, these datasets help researchers measure how well stance detection models generalize across different topics in Arabic.
Arabic datasetsstance detectioncross-target generalizationtweet annotationsentiment analysissarcasm detectiontransformer modelszero-shot learninglarge language modelsbenchmark dataset
Authors
Rasha Albalawi, Nuha Albadi, Hamzah Luqman, Maram Kurdi, Saad Ezzini, Asma Yamani, Ahmed Ashraf
Abstract
Publicly available Arabic datasets for target-specific stance detection remain limited, particularly for evaluating cross-target generalization. This paper presents the Mawqif-v2 Extension, 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.