发现异常文档可预示新话题，为早期信号检测提供新方法。
From Noise to Signal: When Outliers Seed New Topics
- 构建时间分类体系，区分预示性异常与普通文章
- 在11个语言模型上验证，发现少量高共识预示性异常
- 适合关注趋势预测与新闻演化分析的研究者
动态主题建模中的异常项通常被视为噪声，但我们发现部分异常项可作为新兴话题的早期信号。本文提出一种新闻文档轨迹的时间分类体系，刻画文档随时间与主题形成的关系。该体系区分了预示性异常（早于所属主题出现）、强化已有主题或孤立无援的文档。通过捕捉这些轨迹，分类体系将弱信号检测与时间主题建模结合，阐明了单篇文章如何预示、启动或游离于演化中的主题集群。我们在基于11个前沿语言模型的文档嵌入上实现该框架，并在法语氢经济新闻数据集HydroNewsFr上进行回溯评估。跨模型一致性揭示出一小批高共识的预示性异常，提升了标签可信度。定性案例研究进一步展示了具体主题的发展轨迹。
原文摘要 · Abstract (English)
Outliers in dynamic topic modeling are typically treated as noise, yet we show that some can serve as early signals of emerging topics. We introduce a temporal taxonomy of news-document trajectories that defines how documents relate to topic formation over time. It distinguishes anticipatory outliers, which precede the topics they later join, from documents that either reinforce existing topics or remain isolated. By capturing these trajectories, the taxonomy links weak-signal detection with temporal topic modeling and clarifies how individual articles anticipate, initiate, or drift within evolving clusters. We implement it in a cumulative clustering setting using document embeddings from eleven state-of-the-art language models and evaluate it retrospectively on HydroNewsFr, a French news corpus on the hydrogen economy. Inter-model agreement reveals a small, high-consensus subset of anticipatory outliers, increasing confidence in these labels. Qualitative case studies further illustrate these trajectories through concrete topic developments.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。