# Iterative Topic Taxonomy Induction with LLMs: A Case Study of Electoral Advertising

arXiv: https://arxiv.org/abs/2510.15125 · HTML: https://mlsanity.com/paper/2510.15125/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 65 references that are in the map.
- First posted on arXiv 16 Oct 2025.

## Builds on (most cited first, 24 of 24)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Language (Technology) is Power: A Critical Survey of "Bias" in NLP](https://mlsanity.com/paper/2005.14050/) (2020)
- [ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks](https://mlsanity.com/paper/2303.15056/) (2023)
- [BERTopic: Neural topic modeling with a class-based TF-IDF procedure](https://mlsanity.com/paper/2203.05794/) (2022)
- [Efficient Few-Shot Learning Without Prompts](https://mlsanity.com/paper/2209.11055/) (2022)
- [Guiding LLMs The Right Way: Fast, Non-Invasive Constrained Generation](https://mlsanity.com/paper/2403.06988/) (2024)
- [Concept Induction: Analyzing Unstructured Text with High-Level Concepts Using LLooM](https://mlsanity.com/paper/2404.12259/) (2024)
- [Identifying Morality Frames in Political Tweets using Relational Learning](https://mlsanity.com/paper/2109.04535/) (2021)
- [A Holistic Framework for Analyzing the COVID-19 Vaccine Debate](https://mlsanity.com/paper/2205.01817/) (2022)
- [On Microtargeting Socially Divisive Ads: A Case Study of Russia-Linked Ad Campaigns on Facebook](https://mlsanity.com/paper/1808.09218/) (2018)
- [Uncovering Latent Arguments in Social Media Messaging by Employing LLMs-in-the-Loop Strategy](https://mlsanity.com/paper/2404.10259/) (2024)
- [Automatic Generation of Topic Labels](https://mlsanity.com/paper/2006.00127/) (2020)
- [Clandestino or Rifugiato? Anti-immigration Facebook Ad Targeting in Italy](https://mlsanity.com/paper/2103.09224/) (2021)
- [Weakly Supervised Learning for Analyzing Political Campaigns on Facebook](https://mlsanity.com/paper/2210.10669/) (2022)
- [Discovering Latent Themes in Social Media Messaging: A Machine-in-the-Loop Approach Integrating LLMs](https://mlsanity.com/paper/2403.10707/) (2024)
- [Joint Non-negative Matrix Factorization for Learning Ideological Leaning on Twitter](https://mlsanity.com/paper/1711.10251/) (2017)
- [Post-hoc Study of Climate Microtargeting on Social Media Ads with LLMs: Thematic Insights and Fairness Evaluation](https://mlsanity.com/paper/2410.05401/) (2024)
- [Community Detection in Political Twitter Networks using Nonnegative Matrix Factorization Methods](https://mlsanity.com/paper/1608.01771/) (2016)
- [Facebook Ad Engagement in the Russian Active Measures Campaign of 2016](https://mlsanity.com/paper/2012.11690/) (2020)
- [Can LLMs Assist Annotators in Identifying Morality Frames? -- Case Study on Vaccination Debate on Social Media](https://mlsanity.com/paper/2502.01991/) (2025)

## Built on by (most cited first, 1 of 1)

- [Reasoning-Based Refinement of Unsupervised Text Clusters with LLMs](https://mlsanity.com/paper/2604.07562/) (2026)

## Abstract (arXiv)

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.