|
|
--- |
|
|
title: Misogyny Detection It Space |
|
|
emoji: 🌍 |
|
|
colorFrom: blue |
|
|
colorTo: gray |
|
|
sdk: gradio |
|
|
sdk_version: 5.12.0 |
|
|
app_file: app.py |
|
|
pinned: false |
|
|
license: cc-by-nc-sa-4.0 |
|
|
short_description: Misogyny Detection in Italian Text |
|
|
--- |
|
|
|
|
|
# Misogyny Detection in Italian Text |
|
|
|
|
|
This Hugging Face Space demonstrates a **misogyny detection system** fine-tuned on the **AMI (Automatic Misogyny Identification)** dataset for Italian text. The model is based on **BERT** and classifies text into two categories: |
|
|
- **Non-Misogynous (Label = 0)**: Texts that do not contain misogynistic content. |
|
|
- **Misogynous (Label = 1)**: Texts that contain misogynistic content. |
|
|
|
|
|
### How to Use |
|
|
To test the model, simply enter an Italian text in the input field and click "Submit". The model will classify the text as either **Misogynous** or **Non-Misogynous**. |
|
|
|
|
|
### Model Details |
|
|
- **Model Type**: BERT-based model for text classification. |
|
|
- **Language**: Italian. |
|
|
- **License**: CC BY-NC-SA 4.0. |
|
|
- **Repository**: [Hugging Face Model Repository](https://huggingface.co/maiurilorenzo/misogyny-detection-it). |
|
|
- **Dataset**: The model is fine-tuned on the [AMI (Automatic Misogyny Identification) dataset](https://huggingface.co/datasets/sapienzanlp/ami). |
|
|
|
|
|
|
