Vox Aequalis

Illuminating disparities through data

Comment

Vox Aequalis (Equal Voice)

🎯 Inspiration

Inspired by the anime 86, where discrimination and inequality are central themes—only a small number of people are aware of the truth. Vox Aequalis draws from this narrative to highlight real-world biases.

🛠️ What It Does

Vox Aequalis is a web-based platform that analyzes user input and personal context to:

  • Show fair job opportunities and salaries.
  • Visualize discrimination-related data using data analytics.
  • Provide intelligent chatbot support based on intent recognition
  • Raise awareness on bias and inequality through interactive features

🏗️ How I Built It

  • Frontend: Next.js, React, Tailwind CSS, shadcn/ui
  • Backend: Flask, flask-cors, Python
  • Database: JSON-based structured data (e.g., intents, job info)
  • Hosting: Vercel (frontend), Flask runs locally
  • Machine Learning: scikit-learn, Numpy, NLTK for intent classification and analysis

💻 How to Set Up Locally

1. Clone the repository

git clone https://github.com/Yurei04/Vox-Aequalis.git
cd vox-aequalis

2. Set up the frontend (Next.js)

# If frontend is in a subfolder, navigate there first
cd frontend  # skip if not applicable
npm install
npm run dev

Frontend runs at: http://localhost:3000

3. Set up the backend (Flask)

cd ../vox-aequalis-backend
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate
pip install -r requirements.txt

Create a .env file (optional):

FLASK_APP=app.py
FLASK_ENV=development

Then run:

flask run

Backend runs at: http://localhost:5000

4. Connect Frontend to Backend

Ensure your frontend fetches from the Flask API correctly:

fetch('http://localhost:5000/api/your-endpoint')

You can also use an environment variable (e.g., NEXT_PUBLIC_API_URL) for better flexibility.

📄 About the Research Paper

The paper explores the origin of the data used on the website, detailing how it was obtained, interpreted, and summarized. The Vox Aequalis research serves as the foundation for all data presented on the platform.

🧗 Challenges I Ran Into

  • Solo developement caused slow progression of developemnet
  • Finding proper data since this researched required a specific datasets and should have usability score of 10
  • Balancing schoolwork and project deadlines
  • Handling NLP data and training intent models from scratch

🏆 Accomplishments That I'm Proud Of

  • First-time implementation of Python’s NLTK for intent classification
  • Applied machine learning concepts in a real-world scenario
  • Successful integration of frontend, backend, and ML model with minimal resources

📚 What I Learned

  • Strengthened skills in data analytics and full-stack development
  • Learned about the societal impact of algorithmic bias
  • Explored how machine learning and UX design can intersect ethically

🚀 What's Next for Vox Aequalis

  • Expand the intents.json dataset to support more diverse user scenarios
  • Integrate real-time job APIs and verified resources
  • Refactor backend for scalability and deployability
  • Add multilingual support for global accessibility
  • Adding multiple themes for the colorblind
Share this project:

Updates