Skip to content

framonmar7/suicidal-risk-detection

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

17 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

🧠 Suicidal Risk Detection

This is a full-stack web application designed to detect suicidal risk in user-submitted text. It is built using React and Django. The backend uses a trained machine learning model to analyze text and return risk predictions.


🚀 Deployment

When deployed, the project exposes two main entrypoints:


🔬 Model

The NLP model used in this application is a binary classifier based on bert-base-uncased, fine-tuned on a dataset related to depressive and suicidal language in English.

You can explore and download the model on Hugging Face:
👉 https://huggingface.co/framonmar7/depression-classifier

⚠️ This model is experimental and must not be used for real-life decisions. It has not been clinically validated. Its purpose is strictly technical and research-oriented.


⚙️ Setup Instructions

  1. Install the dependencies in a virtual environment:
python -m venv venv
source venv/bin/activate    # or .\venv\Scripts\activate on Windows
pip install -r requirements.txt
  1. Create your environment file:

Copy the .env.example to .env and provide the values:

DJANGO_SECRET_KEY=your-secret-key
DJANGO_DEBUG=True
DJANGO_ALLOWED_HOSTS=localhost,127.0.0.1
  1. Prepare the backend:
python manage.py migrate
python manage.py collectstatic --noinput
  1. Run the development server:
python manage.py runserver

Once the development server is running, you can access the application in your browser at the URL shown in the terminal.


📜 License

This project is released under the MIT License.
You are free to use, modify, and distribute it — with attribution.


👤 Author

Developed by Francisco Jesús Montero Martínez
For suggestions, improvements, or collaboration, feel free to reach out.

About

Web application for identifying suicidal ideation in user-submitted text via NLP.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published