用大模型自动构建选举广告主题分类体系，无需人工标注。
Iterative Topic Taxonomy Induction with LLMs: A Case Study of Electoral Advertising
- 结合无监督聚类与提示推理，迭代生成可解释的主题标签。
- 在2024年美国大选前广告数据上验证，标签语义丰富且一致。
- 适合政治传播分析、舆情监测等需要大规模文本理解的场景。
社交媒体在塑造政治话语中起关键作用，但其海量且快速演变的内容分析仍面临重大挑战。本文提出一个端到端框架，可从无标签文本语料中自动构建可解释的主题分类体系。通过结合无监督聚类与基于提示的推理，该方法利用大语言模型（LLMs）迭代生成分类结构，无需种子集（预定义标签）或领域知识。我们在2024年美国总统大选前的政治广告研究中验证了该框架的有效性。生成的主题分类具有丰富的语义标签，并支持下游分析（如道德框架分析）。人类评估结果显示，结构化、迭代式标注比现有方法产生更一致、更可解释的标签，且适用于大规模政治广告数据分析。
原文摘要 · Abstract (English)
Social media platforms play a pivotal role in shaping political discourse, but analyzing their vast and rapidly evolving content remains a major challenge. We introduce an end-to-end framework for automatically inducing an interpretable topic taxonomy from unlabeled text corpora. By combining unsupervised clustering with prompt-based inference, our method leverages large language models (LLMs) to iteratively construct a taxonomy without requiring seed sets (predefined labels) or domain expertise. We validate the framework through a study of political advertising ahead of the 2024 U.S. presidential election. The induced taxonomy yields semantically rich topic labels and supports downstream analyses, including moral framing, in this setting. Results suggest that structured, iterative labeling yields more consistent and interpretable topic labels than existing approaches under human evaluation, and is practical for analyzing large-scale political advertising data.
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。