Iterative Topic Taxonomy Induction with LLMs: A Case Study of Electoral Advertising
Not on the map. Why?
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.
Key facts. Cited by 1 paper 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
24 of 65 references.
References · 24
- 2020Language Models are Few-Shot Learnerscited by 32,419
- 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
- 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
- 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,898
- 2020Language (Technology) is Power: A Critical Survey of "Bias" in NLPcited by 956
- 2023ChatGPT Outperforms Crowd-Workers for Text-Annotation Taskscited by 870
- 2022BERTopic: Neural topic modeling with a class-based TF-IDF procedurecited by 801
- 2022Efficient Few-Shot Learning Without Promptscited by 137
- 2024Guiding LLMs The Right Way: Fast, Non-Invasive Constrained Generationcited by 101
- 2024Concept Induction: Analyzing Unstructured Text with High-Level Concepts Using LLooMcited by 78
- 2021Identifying Morality Frames in Political Tweets using Relational Learningcited by 26
12 more
- 2022A Holistic Framework for Analyzing the COVID-19 Vaccine Debatecited by 18
- 2018On Microtargeting Socially Divisive Ads: A Case Study of Russia-Linked Ad Campaigns on Facebookcited by 10
- 2024Uncovering Latent Arguments in Social Media Messaging by Employing LLMs-in-the-Loop Strategycited by 9
- 2020Automatic Generation of Topic Labelscited by 8
- 2021Clandestino or Rifugiato? Anti-immigration Facebook Ad Targeting in Italycited by 8
- 2022Weakly Supervised Learning for Analyzing Political Campaigns on Facebookcited by 8
- 2024Discovering Latent Themes in Social Media Messaging: A Machine-in-the-Loop Approach Integrating LLMscited by 8
- 2017Joint Non-negative Matrix Factorization for Learning Ideological Leaning on Twittercited by 5
- 2024Post-hoc Study of Climate Microtargeting on Social Media Ads with LLMs: Thematic Insights and Fairness Evaluationcited by 4
- 2016Community Detection in Political Twitter Networks using Nonnegative Matrix Factorization Methodscited by 3
- 2020Facebook Ad Engagement in the Russian Active Measures Campaign of 2016cited by 2
- 2025Can LLMs Assist Annotators in Identifying Morality Frames? -- Case Study on Vaccination Debate on Social Mediacited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.