Fine-Tuning Monolingual Pre-Trained BERT Models for Sentiment Analysis in Peruvian Slang Contexts
The continuous advancements in natural language processing (NLP) have led to the development of highly effective models such as BERT, RoBERTa, GPT-4, Llama 3, and Gemini. However, adapting these models to specific dialects, especially in languages other than English, remains underexplored, particula...
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Artículo |
| Lenguaje: | inglés |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | Enlace permanente (DOI o Handle) Ver en el sistema de origen Registro tomado de OpenAlex, que lo atribuye a la UPeU. Aún no está en el CRIS de la universidad. |
| Etiquetas: |
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1881750322220630016 |
|---|---|
| author | Sergio E. Calizaya-Milla Jair Santos Fredy Abel Huanca Torres |
| author_browse | Fredy Abel Huanca Torres Jair Santos Sergio E. Calizaya-Milla |
| author_facet | Sergio E. Calizaya-Milla Jair Santos Fredy Abel Huanca Torres |
| author_sort | Sergio E. Calizaya-Milla |
| collection | Producción científica |
| description | The continuous advancements in natural language processing (NLP) have led to the development of highly effective models such as BERT, RoBERTa, GPT-4, Llama 3, and Gemini. However, adapting these models to specific dialects, especially in languages other than English, remains underexplored, particularly in slang or informal language. Our research evaluates monolingual Spanish models that best fit Peruvian colloquial expressions in response to this need. Our approach involved constructing a specialized dataset of 11,276 manually annotated social media comments, preprocessed to retain the unique features of Peruvian slang. We also expanded the models’ vocabulary using a dictionary of Peruvian slang, ensuring better recognition of local expressions. The dataset was used to fine-tune the models, with RoBERTuito demonstrating superior performance, achieving an F1-score of 0.750, significantly outperforming BETO (0.661), BERTuit (0.700), and RoBERTa-BNE (0.696). This research offers a robust solution for sentiment analysis in Peruvian Spanish. It sets a benchmark for adapting monolingual models to linguistic contexts, with applications extending to other dialects and informal language variants. |
| format | Article |
| fuente_str | OpenAlex |
| id | openalex:W7135419706 |
| institution | UPeU |
| language | English |
| publishDate | 2026 |
| publishDateRange | 2026 |
| publishDateSort | 2026 |
| record_format | dspace |
| spelling | openalex:W7135419706Fine-Tuning Monolingual Pre-Trained BERT Models for Sentiment Analysis in Peruvian Slang ContextsSergio E. Calizaya-MillaJair SantosFredy Abel Huanca Torressentiment analysisPeruvian Spanishslang lexiconsocial media commentsRoBERTaBERTBETOcolloquial languagedialect adaptationSentiment Analysis and Opinion MiningTopic ModelingHate Speech and Cyberbullying DetectionThe continuous advancements in natural language processing (NLP) have led to the development of highly effective models such as BERT, RoBERTa, GPT-4, Llama 3, and Gemini. However, adapting these models to specific dialects, especially in languages other than English, remains underexplored, particularly in slang or informal language. Our research evaluates monolingual Spanish models that best fit Peruvian colloquial expressions in response to this need. Our approach involved constructing a specialized dataset of 11,276 manually annotated social media comments, preprocessed to retain the unique features of Peruvian slang. We also expanded the models’ vocabulary using a dictionary of Peruvian slang, ensuring better recognition of local expressions. The dataset was used to fine-tune the models, with RoBERTuito demonstrating superior performance, achieving an F1-score of 0.750, significantly outperforming BETO (0.661), BERTuit (0.700), and RoBERTa-BNE (0.696). This research offers a robust solution for sentiment analysis in Peruvian Spanish. It sets a benchmark for adapting monolingual models to linguistic contexts, with applications extending to other dialects and informal language variants.Articlehttps://doi.org/10.1080/08839514.2026.2641381https://www.tandfonline.com/doi/pdf/10.1080/08839514.2026.2641381?needAccess=trueW7135419706enApplied Artificial Intelligence0883-95141087-65452026-03-14 |
| spellingShingle | sentiment analysis Peruvian Spanish slang lexicon social media comments RoBERTa BERT BETO colloquial language dialect adaptation Sentiment Analysis and Opinion Mining Topic Modeling Hate Speech and Cyberbullying Detection Sergio E. Calizaya-Milla Jair Santos Fredy Abel Huanca Torres Fine-Tuning Monolingual Pre-Trained BERT Models for Sentiment Analysis in Peruvian Slang Contexts |
| title | Fine-Tuning Monolingual Pre-Trained BERT Models for Sentiment Analysis in Peruvian Slang Contexts |
| title_full | Fine-Tuning Monolingual Pre-Trained BERT Models for Sentiment Analysis in Peruvian Slang Contexts |
| title_fullStr | Fine-Tuning Monolingual Pre-Trained BERT Models for Sentiment Analysis in Peruvian Slang Contexts |
| title_full_unstemmed | Fine-Tuning Monolingual Pre-Trained BERT Models for Sentiment Analysis in Peruvian Slang Contexts |
| title_short | Fine-Tuning Monolingual Pre-Trained BERT Models for Sentiment Analysis in Peruvian Slang Contexts |
| title_sort | fine tuning monolingual pre trained bert models for sentiment analysis in peruvian slang contexts |
| topic | sentiment analysis Peruvian Spanish slang lexicon social media comments RoBERTa BERT BETO colloquial language dialect adaptation Sentiment Analysis and Opinion Mining Topic Modeling Hate Speech and Cyberbullying Detection |
| topic_facet | sentiment analysis Peruvian Spanish slang lexicon social media comments RoBERTa BERT BETO colloquial language dialect adaptation Sentiment Analysis and Opinion Mining Topic Modeling Hate Speech and Cyberbullying Detection |
| url | https://doi.org/10.1080/08839514.2026.2641381 https://www.tandfonline.com/doi/pdf/10.1080/08839514.2026.2641381?needAccess=true |
| work_keys_str_mv | AT sergioecalizayamilla finetuningmonolingualpretrainedbertmodelsforsentimentanalysisinperuvianslangcontexts AT jairsantos finetuningmonolingualpretrainedbertmodelsforsentimentanalysisinperuvianslangcontexts AT fredyabelhuancatorres finetuningmonolingualpretrainedbertmodelsforsentimentanalysisinperuvianslangcontexts |