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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Brady, Alexander, Islam, Tunazzina
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912805003722752
author Brady, Alexander
Islam, Tunazzina
author_facet Brady, Alexander
Islam, Tunazzina
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_15125
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Iterative Topic Taxonomy Induction with LLMs: A Case Study of Electoral Advertising
Brady, Alexander
Islam, Tunazzina
Computation and Language
Artificial Intelligence
Computers and Society
Machine Learning
Social and Information Networks
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.
title Iterative Topic Taxonomy Induction with LLMs: A Case Study of Electoral Advertising
topic Computation and Language
Artificial Intelligence
Computers and Society
Machine Learning
Social and Information Networks
url https://arxiv.org/abs/2510.15125