arXiv：cs.LG（机器学习，全量分类）· Alexander Brady, Tunazzina Islam·· 18 小时前AI 评分34
用 LLM 迭代归纳主题分类体系：以选举广告为例
Iterative Topic Taxonomy Induction with LLMs: A Case Study of Electoral Advertising
AI 导读
研究者提出一套端到端框架，结合嵌入向量聚类与 LLM 迭代推理，无需预定义标签或种子主题即可从无标注文本语料中归纳出可解释的主题分类体系。该框架先从文档聚类中合成候选主题，再用所得分类体系为各聚类分配一致的主题标签。团队以 2024 年美国大选前的政治广告为案例进行评估，并用该分类体系支持议题占比、道德框架、广告支出和人群触达模式等下游分析。
正文
Abstract:Social media platforms play a pivotal role in shaping political discourse, but the scale and rapid evolution of online content make systematic analysis difficult. We introduce an end-to-end framework for inducing an interpretable topic taxonomy from unlabeled text corpora. The framework combines embedding-based clustering with iterative large language model (LLM) inference to construct a topic taxonomy without requiring predefined labels or seed topics. It first synthesizes candidate topics from document clusters and then uses the resulting taxonomy to assign consistent topic labels across clusters. We evaluate the approach through a case study of political advertising ahead of the 2024 U.S. presidential election. We use the induced taxonomy to support downstream analyses of issue prevalence, moral framing, advertising spend, and demographic exposure patterns. These results suggest that iterative taxonomy construction can provide a scalable and interpretable approach to organizing large unlabeled text corpora while supporting substantive downstream analysis.
| Comments: | Accepted to AACL-IJCNLP 2026 Findings. Camera-ready |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Machine Learning (cs.LG); Social and Information Networks (cs.SI) |
| Cite as: | arXiv:2510.15125 [cs.CL] |
| (or arXiv:2510.15125v3 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2510.15125 arXiv-issued DOI via DataCite |
Submission history
From: Tunazzina Islam [view email]
[v1]
Thu, 16 Oct 2025 20:30:20 UTC (3,590 KB)
[v2]
Tue, 6 Jan 2026 17:00:07 UTC (1,930 KB)
[v3]
Thu, 1 Oct 2026 04:18:44 UTC (5,583 KB)
来源：arXiv：cs.LG（机器学习，全量分类） · arxiv.org