---
tags:
- text-classification
- toxicity
- Twitter
base_model: dccuchile/bert-base-spanish-wwm-cased
co2_eq_emissions:
  emissions: 1.2345
license: mit
language:
- es
pipeline_tag: text-classification
library_name: transformers
datasets:
- bgonzalezbustamante/toxicity-protests-ES
---

# Fined-tuned BERT for Toxicity Classification in Spanish

This is a fine-tuned BERT model trained using as a base model BETO, which is a BERT base-sized trained specifically for Spanish. The dataset for training this model is a gold standard for protest events for toxicity and incivility in Spanish.

The dataset comprises ~5M data points from three Latin American protest events: (a) protests against the coronavirus and judicial reform measures in Argentina during August 2020; (b) protests against education budget cuts in Brazil in May 2019; and (c) the social outburst in Chile stemming from protests against the underground fare hike in October 2019. We are focusing on interactions in Spanish to elaborate a gold standard for digital interactions in this language, therefore, we prioritise Argentinian and Chilean data.

- [GitHub repository](https://github.com/training-datalab/gold-standard-toxicity).
- [Dataset on Zenodo](https://zenodo.org/doi/10.5281/zenodo.12574288).
- [Reference paper](https://arxiv.org/abs/2409.09741)

**Labels: NONTOXIC and TOXIC.**

## Example of Classification

```python
## Pipeline as a high-level helper
from transformers import pipeline
toxic_classifier = pipeline("text-classification", model="bgonzalezbustamante/bert-spanish-toxicity")

## Non-toxic example
non_toxic = toxic_classifier("Que tengas un excelente día :)")

## Toxic example
toxic = toxic_classifier("Eres un maldito infeliz")

## Print examples
print(non_toxic)
print(toxic)
```

Output:

```
[{'label': 'NONTOXIC', 'score': 0.8723140358924866}]
[{'label': 'TOXIC', 'score': 0.9470418691635132}]
```

## Validation Metrics

- Accuracy: 0.835
- Precision: 0.816
- Recall: 0.886
- F1-Score: 0.849