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.

翻译：立场检测是一项成熟的任务，它将作者对特定目标的态度分类为“支持”、“中立”和“反对”等类别。除了分类立场标签外，我们利用一个长期建立的情感科学框架，沿着效价（消极-积极）和唤醒度（平静-活跃）这两个实值维度来建模立场。这种维度方法捕捉了立场表达背后微妙的情感状态，实现了细粒度的立场分析。为此，我们引入了DimStance，这是首个带有效价-唤醒度（VA）标注的维度立场资源。该资源包含11,746个目标方面，涉及五种语言（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，分析了跨语言的VA模式，并在回归和提示设置下对预训练模型和大语言模型进行了基准测试。结果表明，经过微调的LLM回归器具有竞争力，但在低资源语言中仍存在持续挑战，并且基于令牌的生成方法存在局限性。DimStance为多语言、情感感知的立场分析和基准测试奠定了基础。