Sabert Spanish Sentiment Analysis

🚀 Spanish Sentiment Analysis Classifier

This BERT-based text classifier is designed to detect sentiments in Spanish, developed as a thesis project for the Computer Engineering degree at Universidad de Buenos Aires (UBA).

🚀 Quick Start

This BERT-based text classifier was developed as a thesis project for the Computer Engineering degree at Universidad de Buenos Aires (UBA). The model is designed to detect sentiments in Spanish and was fine-tuned on the dccuchile/bert-base-spanish-wwm-uncased model using a specific set of hyperparameters. It was trained on a dataset containing 11,500 Spanish tweets collected from various regions, both positive and negative. These tweets were sourced from a well-curated combination of TASS datasets.

✨ Features

• Sentiment Detection: Specifically designed to detect sentiments in Spanish text.
• Fine - Tuned Model: Fine - tuned on the dccuchile/bert-base-spanish-wwm-uncased model with specific hyperparameters.
• Trained on Diverse Data: Trained on 11,500 Spanish tweets from various regions, sourced from TASS datasets.

📦 Installation

You can install the required dependencies using pip:

pip install transformers torch

💻 Usage Examples

Basic Usage

from transformers import BertForSequenceClassification, BertTokenizer
model = BertForSequenceClassification.from_pretrained("VerificadoProfesional/SaBERT-Spanish-Sentiment-Analysis")
tokenizer = BertTokenizer.from_pretrained("VerificadoProfesional/SaBERT-Spanish-Sentiment-Analysis")

Advanced Usage

def predict(model,tokenizer,text,threshold = 0.5):   
        inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True, max_length=128)
        with torch.no_grad():
            outputs = model(**inputs)
        
        logits = outputs.logits
        probabilities = torch.softmax(logits, dim=1).squeeze().tolist()
        
        predicted_class = torch.argmax(logits, dim=1).item()
        if probabilities[predicted_class] <= threshold and predicted_class == 1:
            predicted_class = 0
  
        return bool(predicted_class), probabilities

text = "Your Spanish news text here"
predicted_label,probabilities = predict(model,tokenizer,text)
print(f"Text: {text}")
print(f"Predicted Class: {predicted_label}")
print(f"Probabilities: {probabilities}")

📚 Documentation

Team Members

• Azul Fuentes
• Dante Reinaudo
• Lucía Pardo
• Roberto Iskandarani

Model Details

Metrics

The model's performance was evaluated using the following metrics:

• Accuracy = 86.47%
• F1 - Score = 86.47%
• Precision = 86.46%
• Recall = 86.51%

📄 License

• Apache License 2.0
• TASS Dataset license

🔗 Acknowledgments

Special thanks to DCC UChile for the base Spanish BERT model and to all contributors to the dataset used for training.