metadata
license: cc-by-nc-4.0
pipeline_tag: text-classification
tags:
- BERT
- BETO
- spanish
- sentiment-analysis
- text-classification
- NLP
- transformers
widget:
- text: Me encanta usar este modelo para análisis de sentimiento.
example_title: Sentimiento Positivo
- text: Este producto no cumplió mis expectativas.
example_title: Sentimiento Negativo
- text: El clima está bastante agradable hoy.
example_title: Sentimiento Neutro
- text: Me siento devastado por las noticias recientes.
example_title: Sentimiento Negativo
- text: La película estuvo regular, no fue ni buena ni mala.
example_title: Sentimiento Neutro
language:
- es
library_name: transformers
🌐 BETO Spanish Sentiment Analysis Model 📝🤖
📌 Summary in English: This sentiment analysis model is based on the BETO, a Spanish variant of BERT.
🎯📊 Model Performance
- Accuracy in 3 categories: 67.59%
- Classification Report:
| Sentiment | Precision | Recall | F1-Score | Support |
|---|---|---|---|---|
| Negative | 0.64 | 0.72 | 0.68 | 15844 |
| Neutral | 0.64 | 0.54 | 0.58 | 22721 |
| Positive | 0.73 | 0.79 | 0.76 | 22233 |
| Weighted Avg | 0.67 | 0.68 | 0.67 | 60798 |
📔🔗 Try it on Google Colab! 🌐
Model and Data Sources
Cañete, J., Chaperon, G., Fuentes, R., Pérez, J., & Bustos, B. (2020). Spanish Pre-Trained BERT Model and Evaluation Data. Recuperado de https://arxiv.org/abs/2308.02976
SEPLN TASS (2012). Workshop on Semantic Analysis at SEPLN
License Disclaimer
The license CC BY 4.0 best describes our intentions for our work. However we are not sure that all the datasets used to train BETO have licenses compatible with CC BY 4.0 (specially for commercial use). Please use at your own discretion and verify that the licenses of the original text resources match your needs.