发表机构
Valencian Research Institute for Artificial Intelligence; Universitat Politècnica de València; Valencian Graduate School and Research Network of Artificial Intelligence（瓦伦西亚人工智能研究中心; 瓦伦西亚理工大学; 瓦伦西亚人工智能研究生学院及研究网络）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对西班牙语心理健康筛查的资源与分析难题，开发适配心理健康领域的西班牙语基础模型及增量上下文扩展方法，结合后在三个基准上提升了早期风险检测性能并降低延迟，模型公开可用。
AI 中文摘要
心理健康障碍的早期检测常受限于西班牙语专业资源的匮乏，以及分析社交媒体长期发帖历史的困难。本文针对这些挑战，提出三项核心贡献：第一，引入三个专门适配心理健康领域的西班牙语基础模型，通过领域特定预训练实现；第二，提出增量上下文扩展（Incremental Context Expansion, ICE），这是一种专为早期检测设计的自动重标注方法，ICE可识别累积信息提供足够障碍证据的时间点，生成更具信息量的训练样本；第三，使用ICE方法生成的样本提供一组微调模型，用于早期风险检测任务。我们在三个西班牙语基准上的结果显示，将这些专业模型与ICE结合可提升当前最优水平，在保持高性能的同时降低检测延迟，所有模型均公开可用。
英文摘要
Early detection of mental health disorders is often limited by the lack of specialized resources in Spanish and the difficulty of analyzing long histories of social media posts. This paper addresses these challenges through three main contributions. First, we introduce three Spanish foundational models specifically adapted to the mental health domain through domain-specific pre-training. Second, we propose Incremental Context Expansion (ICE), an automatic relabeling methodology designed for early detection. ICE identifies the point at which cumulative messages provide enough evidence of a disorder, generating more informative training samples. Third, we provide a set of fine-tuned models using the samples generated with the ICE methodology for early risk detection tasks. Our results on three Spanish benchmarks show that combining these specialized models with ICE improves the state-of-the-art, reducing detection latency while maintaining high performance. All models are publicly available.
