Saved in:
Bibliographic Details
Main Authors: Tyagi, Nemika, Guevara, Nelvin Licona, Kellert, Olga
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.03334
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908690432393216
author Tyagi, Nemika
Guevara, Nelvin Licona
Kellert, Olga
author_facet Tyagi, Nemika
Guevara, Nelvin Licona
Kellert, Olga
contents 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-Guaraní. 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-Guaraní 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 Guaraní 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.
format Preprint
id arxiv_https___arxiv_org_abs_2512_03334
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Modeling Topics and Sociolinguistic Variation in Code-Switched Discourse: Insights from Spanish-English and Spanish-Guaraní
Tyagi, Nemika
Guevara, Nelvin Licona
Kellert, Olga
Computation and Language
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-Guaraní. 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-Guaraní 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 Guaraní 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.
title Modeling Topics and Sociolinguistic Variation in Code-Switched Discourse: Insights from Spanish-English and Spanish-Guaraní
topic Computation and Language
url https://arxiv.org/abs/2512.03334