Latent Topic Synthesis: Leveraging LLMs for Electoral Ad Analysis
This work enables scalable, interpretable analysis of political messaging on social media for researchers, policymakers, and the public, though it is incremental as it combines existing methods like unsupervised clustering and LLMs for a specific domain.
The authors tackled the challenge of analyzing vast political ad content on social media by introducing an end-to-end framework that automatically generates an interpretable topic taxonomy from unlabeled data, applying it to Meta political ads from the 2024 U.S. Presidential election to reveal that voting and immigration ads dominated spending and impressions, while abortion and election-integrity achieved disproportionate reach.
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 generating an interpretable topic taxonomy from an unlabeled corpus. By combining unsupervised clustering with prompt-based labeling, our method leverages large language models (LLMs) to iteratively construct a taxonomy without requiring seed sets or domain expertise. We apply this framework to a large corpus of Meta (previously known as Facebook) political ads from the month ahead of the 2024 U.S. Presidential election. Our approach uncovers latent discourse structures, synthesizes semantically rich topic labels, and annotates topics with moral framing dimensions. We show quantitative and qualitative analyses to demonstrate the effectiveness of our framework. Our findings reveal that voting and immigration ads dominate overall spending and impressions, while abortion and election-integrity achieve disproportionate reach. Funding patterns are equally polarized: economic appeals are driven mainly by conservative PACs, abortion messaging splits between pro- and anti-rights coalitions, and crime-and-justice campaigns are fragmented across local committees. The framing of these appeals also diverges--abortion ads emphasize liberty/oppression rhetoric, while economic messaging blends care/harm, fairness/cheating, and liberty/oppression narratives. Topic salience further reveals strong correlations between moral foundations and issues. Demographic targeting also emerges. This work supports scalable, interpretable analysis of political messaging on social media, enabling researchers, policymakers, and the public to better understand emerging narratives, polarization dynamics, and the moral underpinnings of digital political communication.