NoraAlt/Mawqif_Stance-Detection
收藏资源简介：
--- task_categories: - text-classification language: - ar pretty_name: 'Mawqif: Stance Detection' size_categories: - 1K<n<10K tags: - Stance Detection - Sentiment Analysis - Sarcasm Detection --- # Mawqif: A Multi-label Arabic Dataset for Target-specific Stance Detection - *Mawqif* is the first Arabic dataset that can be used for target-specific stance detection. - This is a multi-label dataset where each data point is annotated for stance, sentiment, and sarcasm. - We benchmark *Mawqif* dataset on the stance detection task and evaluate the performance of four BERT-based models. Our best model achieves a macro-F1 of 78.89\%. # Mawqif Statistics - This dataset consists of **4,121** tweets in multi-dialectal Arabic. Each tweet is annotated with a stance toward one of three targets: “COVID-19 vaccine,” “digital transformation,” and “women empowerment.” In addition, it is annotated with sentiment and sarcasm polarities. - The following figure illustrates the labels’ distribution across all targets, and the distribution per target. <img width="738" alt="dataStat-2" src="https://user-images.githubusercontent.com/31368075/188299057-54d04e87-802d-4b0e-b7c6-56bdc1078284.png"> # Interactive Visualization To browse an interactive visualization of the *Mawqif* dataset, please click [here](https://public.tableau.com/views/MawqifDatasetDashboard/Dashboard1?:language=en-US&publish=yes&:display_count=n&:origin=viz_share_link) - *You can click on visualization components to filter the data by target and by class. **For example,** you can click on “women empowerment" and "against" to get the information of tweets that express against women empowerment.* # Citation If you feel our paper and resources are useful, please consider citing our work! ``` @inproceedings{alturayeif-etal-2022-mawqif, title = "Mawqif: A Multi-label {A}rabic Dataset for Target-specific Stance Detection", author = "Alturayeif, Nora Saleh and Luqman, Hamzah Abdullah and Ahmed, Moataz Aly Kamaleldin", booktitle = "Proceedings of the The Seventh Arabic Natural Language Processing Workshop (WANLP)", month = dec, year = "2022", address = "Abu Dhabi, United Arab Emirates (Hybrid)", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2022.wanlp-1.16", pages = "174--184" } ```
--- task_categories: - 文本分类 language: - 阿拉伯语 pretty_name: 'Mawqif：立场检测(Stance Detection)' size_categories: - 样本量介于1000至10000之间 tags: - 立场检测(Stance Detection) - 情感分析(Sentiment Analysis) - 讽刺检测(Sarcasm Detection) --- # Mawqif：面向目标特定立场检测的多标签阿拉伯语数据集 - *Mawqif*是首个可用于目标特定立场检测的阿拉伯语数据集。 - 本数据集为多标签类型，每条数据均针对立场、情感与讽刺性进行标注。 - 我们在立场检测任务上对Mawqif数据集开展了基准测试，并评估了4种基于BERT的模型的性能，其中最优模型的宏F1值达到78.89%。 # Mawqif 统计信息 - 本数据集包含**4121**条多方言阿拉伯语推文。每条推文均针对三个目标之一进行立场标注：“新冠疫苗(COVID-19 vaccine)”、“数字化转型(digital transformation)”与“赋权女性(women empowerment)”。此外，推文还标注了情感与讽刺极性。 - 下图展示了全目标维度下的标签分布情况，以及分目标的标签分布情况。 <img width="738" alt="dataStat-2" src="https://user-images.githubusercontent.com/31368075/188299057-54d04e87-802d-4b0e-b7c6-56bdc1078284.png"> # 交互式可视化 如需浏览Mawqif数据集的交互式可视化内容，请点击[此处](https://public.tableau.com/views/MawqifDatasetDashboard/Dashboard1?:language=en-US&publish=yes&:display_count=n&:origin=viz_share_link) - 您可点击可视化组件，按目标与类别筛选数据。**例如**，您可点击“赋权女性”与“反对”，即可获取表达反对赋权女性立场的推文相关信息。 # 引用 若您认为本文与相关资源对您的研究有所帮助，请考虑引用本工作！ @inproceedings{alturayeif-etal-2022-mawqif, title = "Mawqif: A Multi-label {A}rabic Dataset for Target-specific Stance Detection", author = "Alturayeif, Nora Saleh and Luqman, Hamzah Abdullah and Ahmed, Moataz Aly Kamaleldin", booktitle = "Proceedings of the The Seventh Arabic Natural Language Processing Workshop (WANLP)", month = dec, year = "2022", address = "Abu Dhabi, United Arab Emirates (Hybrid)", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2022.wanlp-1.16", pages = "174--184" }
Mawqif: A Multi-label Arabic Dataset for Target-specific Stance Detection
概述
- 名称：Mawqif
- 任务类别：文本分类
- 语言：阿拉伯语
- 数据集大小：1K<n<10K
- 标签：立场检测、情感分析、讽刺检测
详细信息
- 数据集类型：多标签数据集，每个数据点标注了立场、情感和讽刺。
- 数据集内容：包含4,121条多方言阿拉伯语推文，每条推文针对以下三个目标之一标注立场：“COVID-19疫苗”、“数字化转型”和“女性赋权”。此外，还标注了情感和讽刺倾向。
- 模型评估：在立场检测任务上，使用四种基于BERT的模型进行基准测试，最佳模型达到78.89%的宏F1分数。
可视化
- 提供交互式可视化工具，可按目标和类别过滤数据。
引用
@inproceedings{alturayeif-etal-2022-mawqif, title = "Mawqif: A Multi-label {A}rabic Dataset for Target-specific Stance Detection", author = "Alturayeif, Nora Saleh and Luqman, Hamzah Abdullah and Ahmed, Moataz Aly Kamaleldin", booktitle = "Proceedings of the The Seventh Arabic Natural Language Processing Workshop (WANLP)", month = dec, year = "2022", address = "Abu Dhabi, United Arab Emirates (Hybrid)", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2022.wanlp-1.16", pages = "174--184" }
