MoodAnalyzer 🧠

An AI-powered mental health assessment platform that provides real-time emotional analysis and personalized recommendations using machine learning.

🚀 Features

• Real-time Emotion Detection: Uses Google's GoEmotions dataset with TF-IDF and Logistic Regression
• Mental Health Risk Assessment: Hybrid ML model for student mental health prediction
• User Clustering: K-Means clustering with 19+ engineered features for personality profiling
• 6-Step Assessment: Comprehensive user evaluation (Registration → Mood → Lifestyle → Coping → Journal → Results)
• Interactive Web Interface: Responsive design with real-time analysis

🛠️ Tech Stack

• Backend: Flask (Python)
• Frontend: HTML, CSS, JavaScript
• Machine Learning: scikit-learn, pandas, numpy, NLTK
• Datasets: GoEmotions (28 emotions), Student Mental Health Survey
• APIs: RESTful JSON endpoints

📊 Machine Learning Models

1. Emotion Classifier: TF-IDF + Logistic Regression trained on GoEmotions dataset
2. Risk Predictor: Hybrid model using demographic and behavioral data
3. User Clustering: K-Means algorithm with feature engineering

🏗️ Project Structure

MoodAnalyzer/
├── app.py                 # Main Flask application
├── frontend/              # HTML/CSS/JS interface
├── ml_models/             # Custom ML implementations
├── data/                  # Training datasets
├── services/              # API services
├── utils/                 # Helper utilities
└── requirements.txt       # Dependencies

🚀 Quick Start

1. Install Dependencies

   pip install -r requirements.txt

2. Run Application

   python app.py

3. Access Application

   http://localhost:5000
   

💡 How It Works

1. User Assessment: 6-step form collects comprehensive user data
2. Data Processing: Features engineered for ML model input
3. ML Analysis: 3 models analyze emotions, risk, and personality
4. Results Generation: Personalized insights and recommendations
5. Real-time Display: Interactive results with confidence scores

🎯 Key Achievements

• Built end-to-end ML pipeline with real-world datasets
• Implemented production-ready Flask API with error handling
• Created responsive web interface with vanilla JavaScript
• Achieved real-time processing with intelligent fallback systems
• Integrated multiple ML techniques for comprehensive analysis

📈 Future Enhancements

• Mobile application development
• Additional ML models for mood prediction
• Integration with wearable devices
• Expanded dataset training

---

Built with ❤️ for mental health awareness and AI-powered healthcare solutions.