发表机构
Augustana College; Dakota State University（奥古斯塔纳学院; 达科他州立大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究针对社交媒体信息操作中重复内容作为协调证据的局限，提出通用/非通用区分方法，利用LLM标注与嵌入分类，发现非通用活动揭示更集中的协调结构。
AI 中文摘要
重复内容被广泛用于研究社交媒体信息操作（IOs）中的协调行为，但并非所有的重复都能提供同等有意义的协调证据。通用的、可重复使用的或低信息量的帖子在投射到协调图中时，可能会产生嘈杂的账号-账号链接。我们使用来自六个俄罗斯Twitter信息操作数据集的187,000条英语推文来研究这个问题。我们引入了重复活动的通用/非通用区分，使用带有独立人工验证的LLM辅助协议对推文进行标注，并训练基于句子嵌入的有监督分类器来扩展标签。我们使用词汇相似性和两种基于嵌入的方法构建重复活动。通用活动在词汇匹配下很少见，但在基于嵌入的方法检测到的活动中占近39%。将图限制为非通用活动会减小图的大小和最大连通分量，同时增加密度，表明存在一个更小但更集中的协调结构。这些发现表明，基于重复的协调分析应考虑文本相似性和语义特异性。
英文摘要
Duplicate content is widely used to study coordinated behavior in social media information operations (IOs), but not all repetition provides equally meaningful evidence of coordination. Generic, reusable, or low-information posts may create noisy account-account links when projected into coordination graphs. We study this problem using 187,000 English-language tweets from six Russian Twitter Information Operations datasets. We introduce a generic/non-generic distinction for duplicate campaigns, label tweets using an LLM-assisted protocol with independent human validation, and train supervised classifiers over sentence embeddings to scale the labels. We construct duplicate campaigns using lexical similarity and two embedding-based methods. Generic campaigns are rare under lexical matching but account for nearly 39% of campaigns detected by embedding-based methods. Restricting graphs to non-generic campaigns reduces graph size and the largest connected component while increasing density, suggesting a smaller but more focused coordination structure. These findings show that duplicate-based coordination analysis should consider both textual similarity and semantic specificity.
CommentsAccepted in the 11th Workshop on Natural User-generated Text (W-NUT collocated with EMNLP 2026)
