用大模型识别社交媒体上的操纵性政治叙事，区分真假批评。
LLM-based Detection of Manipulative Political Narratives
- 先用提示词过滤出操纵性内容，再聚类分析。
- 从120万条帖子中发现41个操纵性叙事群组。
- 无需预设类别，能发现新出现的操纵话术。
我们提出一种新型计算框架，用于检测与结构化操纵性政治叙事。随着政治讨论转向社交媒体，这一任务愈发重要。主要挑战在于区分操纵性叙事与合法批评，部分帖子甚至会将真实事件重新包装为操纵性语境。为此，我们采用包含已知宣传策略与合法批评的细粒度少样本提示词，使推理模型对帖子进行标注，仅保留操纵性内容用于后续处理。剩余帖子经由UMAP降维嵌入后，使用HDBSCAN进行聚类，以发现叙事群组。该无监督方法不依赖预设类别，可挖掘新型叙事模式。最终，通过推理模型解析每个聚类背后的叙事逻辑。该方法应用于超过120万条社交媒体帖子，成功识别出41个不同操纵性叙事集群。
原文摘要 · Abstract (English)
We present a new computational framework for detecting and structuring manipulative political narratives. A task that became more important due to the shift of political discussions to social media. One of the primary challenges thereby is differentiating between manipulative political narratives and legitimate critiques. Some posts may also reframe actual events within a manipulative context. To achieve good clustering results, we filter manipulative posts beforehand using a detailed few-shot prompt that combines documented campaign narratives with legitimate criticisms to differentiate them. This prompt enables a reasoning model to assign labels, retaining only manipulative narrative posts for further processing. The remaining posts are subsequently embedded and dimensionality-reduced using UMAP, before HDBSCAN is applied to uncover narrative groups. A key advantage of this unsupervised approach is its independence from a predefined list of target categories, enabling it to uncover new narrative clusters. Finally, a reasoning model is employed to uncover the narrative behind each cluster. This approach, applied to over 1.2 million social media posts, effectively identified 41 distinct manipulative narrative clusters by integrating prompt-based filtering with unsupervised clustering.
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。