Sentiment Analysis in Mexican Spanish: A Comparison Between Fine-Tuning and In-Context Learning with Large Language Models

Tomás Bernal-Beltrán, Mario Andrés Paredes-Valverde, María del Pilar Salas-Zárate, José Antonio García-Díaz and Rafael Valencia-García ()
Additional contact information
Tomás Bernal-Beltrán: Departamento de Informática y Sistemas, Universidad de Murcia, Campus de Espinardo, 30100 Murcia, Spain
Mario Andrés Paredes-Valverde: Tecnológico Nacional de México, I.T.S. Teziutlán, Fracción I y II, Teziutlán 73960, Puebla, Mexico
María del Pilar Salas-Zárate: Tecnológico Nacional de México, I.T.S. Teziutlán, Fracción I y II, Teziutlán 73960, Puebla, Mexico
José Antonio García-Díaz: Departamento de Informática y Sistemas, Universidad de Murcia, Campus de Espinardo, 30100 Murcia, Spain
Rafael Valencia-García: Departamento de Informática y Sistemas, Universidad de Murcia, Campus de Espinardo, 30100 Murcia, Spain

Future Internet, 2025, vol. 17, issue 10, 1-23

Abstract: The proliferation of social media has made Sentiment Analysis an essential tool for understanding user opinions, particularly in underrepresented language variants such as Mexican Spanish. Recent advances in Large Language Models have made effective sentiment analysis through in-context learning techniques, reducing the need for supervised training. This study compares the performance of zero and few-shot with traditional fine-tuning approaches of tourism-related texts in Mexican Spanish. Two annotated datasets from the REST-MEX 2022 and 2023 shared tasks were used for this purpose. Results show that fine-tuning, particularly with the MarIA model, achieves the best overall performance. However, modern LLMs that use in-context learning strategies, such as Mixtral 8x7B for zero-shot and Mistral 7B for few-shot, demonstrate strong potential in low-resource settings by closely approximating the accuracy of fine-tuned models, suggesting that in-context learning is a viable alternative to fine-tuning for sentiment analysis in Mexican Spanish when labeled data is limited. These approaches can enable intelligent, data-driven digital services with applications in tourism platforms and urban information systems that enhance user experience and trust in large-scale socio-technical ecosystems.

Keywords: sentiment analysis (SA); in-context learning (ICL); prompt-tuning; fine-tuning; large language models (LLMs); natural language processing (NLP); social media analytics; smart tourism; data-driven services (search for similar items in EconPapers)
JEL-codes: O3 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1999-5903/17/10/445/pdf (application/pdf)
https://www.mdpi.com/1999-5903/17/10/445/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jftint:v:17:y:2025:i:10:p:445-:d:1760980

Access Statistics for this article

Future Internet is currently edited by Ms. Grace You

More articles in Future Internet from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().