LLM quantifies sexual content in reggaeton lyrics across two decades

Researchers have developed a novel method utilizing a large language model (LLM) to quantify thematic content, specifically sexual explicitness, in song lyrics. This approach was applied to a dataset of 1,259 songs by 12 reggaeton artists spanning from 2002 to 2025. The study analyzed thematic changes over time and compared the LLM's sexual-explicitness score against Spotify's explicit content flag. The researchers have made their data collection code, scoring prompt, and corpus publicly available to facilitate replication and further research. AI

IMPACT Provides a new method for analyzing thematic content in creative works, potentially applicable to other genres or media.

RANK_REASON Academic paper detailing a new methodology for content analysis using LLMs. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CL →

• arXiv
• Hugging Face
• reggaeton
• Spotify

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →