DimStance：多语言数据集用于维度立场分析
DimStance: Multilingual Datasets for Dimensional Stance Analysis
AI总结：
DimStance通过引入valence-arousal维度标注，为多语言立场分析提供首个数据集，评估模型在回归和提示设置下的性能，揭示了细粒度立场分析的挑战与前景。
摘要：
立场检测是一个已确立的任务，它将作者对特定目标的态度分类为赞成、中立和反对等类别。在类别化立场标签之外，我们利用一个长期存在的情感科学框架，以valence（负面-正面）和arousal（平静-活跃）的实值维度来建模立场。这种维度方法捕捉了立场表达下的细微情感状态，使细粒度的立场分析成为可能。为此，我们引入了DimStance，这是首个具有valence-arousal（VA）注释的维度立场资源。该资源包含11,746个目标方面，涵盖五种语言（英语、德语、中文、尼日利亚皮钦语和斯瓦希里语）和两个领域（政治和环境保护）的7,365篇文本。为了促进立场VA预测的评估，我们制定了维度立场回归任务，分析跨语言VA模式，并在回归和提示设置下基准测试预训练和大型语言模型。结果表明，微调的LLM回归器表现出竞争力，低资源语言仍面临挑战，token-based生成存在局限性。DimStance为多语言、情感感知的立场分析和基准测试提供了基础。
英文摘要：
Stance detection is an established task that classifies an author's attitude toward a specific target into categories such as Favor, Neutral, and Against. Beyond categorical stance labels, we leverage a long-established affective science framework to model stance along real-valued dimensions of valence (negative-positive) and arousal (calm-active). This dimensional approach captures nuanced affective states underlying stance expressions, enabling fine-grained stance analysis. To this end, we introduce DimStance, the first dimensional stance resource with valence-arousal (VA) annotations. This resource comprises 11,746 target aspects in 7,365 texts across five languages (English, German, Chinese, Nigerian Pidgin, and Swahili) and two domains (politics and environmental protection). To facilitate the evaluation of stance VA prediction, we formulate the dimensional stance regression task, analyze cross-lingual VA patterns, and benchmark pretrained and large language models under regression and prompting settings. Results show competitive performance of fine-tuned LLM regressors, persistent challenges in low-resource languages, and limitations of token-based generation. DimStance provides a foundation for multilingual, emotion-aware, stance analysis and benchmarking.
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。
