Skip to content

Latest commit

 

History

4 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 

Repository files navigation

Seba - AI Educational Platform with Emotion-Aware Virtual Teacher

Overview

Seba is an AI-powered educational platform designed to provide personalized, emotionally intelligent tutoring for students.

The system addresses major challenges in the Egyptian education system such as:

  • Overcrowded classrooms
  • Lack of personalized learning
  • High cost of private tutoring

Seba transforms traditional LMS into an intelligent virtual teacher using advanced AI techniques like RAG and emotion detection.


Key Features

  • Emotion-aware AI Tutor (detects student feelings)
  • Curriculum-based responses using RAG
  • Bilingual support (Arabic / English)
  • Learning analytics dashboard
  • Dynamic quiz generation
  • Microservices architecture with Docker

System Architecture

  • Frontend: React (RTL support for Arabic)
  • Backend: FastAPI (Python)
  • AI Engine: RAG + NLP models
  • Vector Database: FAISS
  • Emotion Detection: RoBERTa (GoEmotions)
  • Deployment: Docker & Microservices

How It Works

  1. Student sends a question (Arabic or English)

  2. System analyzes emotion using NLP

  3. Query is processed using Hybrid RAG:

    • Semantic Search (FAISS)
    • Keyword Search (BM25)
  4. AI generates response based on curriculum

  5. System adapts explanation based on student emotion

  6. Dynamic quiz is generated based on performance


Tech Stack

  • Python (FastAPI, NLP libraries)
  • Hugging Face Transformers
  • FAISS (Vector Search)
  • React + TypeScript
  • Docker & Docker Compose
  • SQLite / PostgreSQL

Installation & Setup

Using Docker (Recommended)

docker-compose up --build

Manual Setup

Backend:

cd backend
pip install -r requirements.txt
uvicorn app:app --reload

Frontend:

cd frontend
npm install
npm run dev

Project Objectives

  • Build an emotion-aware AI tutor
  • Implement Hybrid RAG system
  • Support Arabic + English (RTL)
  • Provide learning analytics dashboard
  • Ensure scalable architecture
  • Follow WCAG accessibility standards

Use Cases

  • Students needing personalized explanations
  • Teachers tracking student performance
  • Reducing dependency on private tutoring

Screenshots

image image image image image image image image

Future Work

  • Voice interaction (Speech-to-Text)
  • Mobile application
  • Advanced deep learning models
  • Cloud deployment

Team

  • Nehal Kamal & teammates in graduation project

Notes

This project is developed as a Graduation Project for the Artificial Intelligence Engineering Program at Mansoura University.

It demonstrates the integration of:


About

A smart AI tutoring system that combines natural language processing and machine learning to provide adaptive educational assistance.

Resources

Stars

1 star

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages