研究人员开发了TENSOR，一种新颖的无监督方法，用于检测社交媒体上参与信息操作（IO）的用户。TENSOR结合了行为和语言模式，利用时间点过程（TPPs）识别异常的时间活动，并使用LLM生成的分数来完善检测。该方法旨在通过不依赖于用户协调的过度简化假设来克服现有监督和无监督技术的局限性。在五个真实世界IO数据集上的实验表明，TENSOR的性能优于基线方法。 AI
影响 这项研究可能有助于开发更有效的工具，以识别和减轻社交媒体上的协同虚假信息活动。
排序理由 该集群包含一篇详细介绍AI中异常检测新方法的 ist 研究论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2607.05855v1 Announce Type: cross Abstract: Information Operations on social media networks have been identified as a significant threat to democracy and modern society, but they are challenging and expensive to detect by humans. Existing supervised IO detection methods fai…
Information Operations on social media networks have been identified as a significant threat to democracy and modern society, but they are challenging and expensive to detect by humans. Existing supervised IO detection methods fail to capture the dynamic nature of evolving IO use…