Modeling Topics and Sociolinguistic Variation in Code-Switched Discourse: Insights from Spanish-English and Spanish-Guaran\'i

TL;DR

This paper introduces an LLM-assisted annotation pipeline for analyzing sociolinguistic and topical patterns in code-switched discourse across Spanish-English and Spanish-Guaraní, revealing systematic sociolinguistic links and diglossic divisions.

Contribution

It presents a novel LLM-based method for automated sociolinguistic annotation in bilingual discourse, enabling large-scale analysis of sociolinguistic patterns in low-resource languages.

Findings

Systematic links between gender, language dominance, and discourse functions.

A clear diglossic division between formal Guaraní and informal Spanish.

Replication of earlier sociolinguistic observations with corpus-scale data.

Abstract

This study presents an LLM-assisted annotation pipeline for the sociolinguistic and topical analysis of bilingual discourse in two typologically distinct contexts: Spanish-English and Spanish-Guaran\'i. Using large language models, we automatically labeled topic, genre, and discourse-pragmatic functions across a total of 3,691 code-switched sentences, integrated demographic metadata from the Miami Bilingual Corpus, and enriched the Spanish-Guaran\'i dataset with new topic annotations. The resulting distributions reveal systematic links between gender, language dominance, and discourse function in the Miami data, and a clear diglossic division between formal Guaran\'i and informal Spanish in Paraguayan texts. These findings replicate and extend earlier interactional and sociolinguistic observations with corpus-scale quantitative evidence. The study demonstrates that large language models can reliably recover interpretable sociolinguistic patterns traditionally accessible only through manual annotation, advancing computational methods for cross-linguistic and low-resource bilingual research.