🎓 Research Profiler AI - Complete Guide

A modern, AI-powered research publication analysis system with automatic evaluation and beautiful UI.

---

✨ What's New

🎨 Modern Streamlit Frontend

• Shadcn-inspired design with gradient backgrounds
• Split-screen results - Data preview + AI analysis side-by-side
• Interactive charts with Plotly
• Multiple input methods - Single author, CSV, or BibTeX
• One-click exports - Excel, Word, JSON

🤖 Automatic AI Evaluation

• Impact prediction with ML models (0-100+ score)
• Trend analysis with 3-year forecasts
• Strategic recommendations from AI
• H-index & i10-index calculation
• Emerging topics identification

---

🚀 Quick Start (Easiest Method)

Windows Users:

Just double-click: START_APP.bat

This will:

1. Start Flask API on port 5000
2. Start Streamlit on port 8501
3. Open browser automatically

Done! 🎉

---

📋 Manual Start (All Platforms)

Prerequisites:

# Install Python packages
pip install -r API/requirements.txt
pip install -r requirements_streamlit.txt

Step 1: Start Flask API

# Terminal 1
cd API
python main.py

Flask runs on: http://localhost:5000

Step 2: Start Streamlit Frontend

# Terminal 2
streamlit run streamlit_app.py

Streamlit opens at: http://localhost:8501

---

📁 Project Structure

Profyler/
├── API/                              # Backend Flask API
│   ├── main.py                       # Flask app with AI integration
│   ├── fetchers.py                   # Academic API fetchers
│   ├── requirements.txt              # API dependencies
│   ├── ai_models/                    # AI/ML models
│   │   ├── impact_predictor.py       # Impact prediction ML
│   │   └── trend_analyzer.py         # Trend analysis ML
│   ├── test_simple.py                # API test script
│   ├── AI_ML_FEATURES.md             # AI documentation
│   ├── AI_QUICK_START.md             # AI quick guide
│   └── AUTOMATIC_AI_EVALUATION.md    # Auto-eval docs
│
├── streamlit_app.py                  # Modern Streamlit frontend
├── requirements_streamlit.txt        # Frontend dependencies
├── START_APP.bat                     # Quick start script (Windows)
├── STREAMLIT_GUIDE.md                # Frontend guide
└── README.md                         # This file

---

🎯 Features Overview

1. Multi-Source Data Fetching

• Semantic Scholar: Abstracts, citations, affiliations
• DBLP: Computer science publications
• CrossRef: DOI-based metadata
• Intelligent merging: Combines best data from all sources

2. AI/ML Analysis

• Impact Prediction:

  • 25+ features extracted per paper
  • Ensemble ML (RandomForest + GradientBoosting)
  • Scores: 0-100+ (Low/Medium/High/Very High/Exceptional)

• Trend Analysis:

  • Publication trends (Growing/Stable/Declining)
  • 3-year future predictions
  • Emerging research topics
  • Keyword evolution tracking

• Research Metrics:

  • H-index calculation
  • i10-index calculation
  • Research diversity score
  • Collaboration patterns

• Strategic Insights:

  • AI-generated recommendations
  • Collaboration suggestions
  • Venue recommendations
  • Focus area guidance

3. Beautiful UI

• Modern Design: Gradient backgrounds, smooth animations
• Responsive: Works on desktop, tablet, mobile
• Split View: Data + AI analysis side-by-side
• Interactive: Filterable tables, zoomable charts
• Export Options: Excel, Word, JSON

---

📊 Usage Examples

Example 1: Quick Single Author Analysis

1. Open Streamlit app
2. Select "Single Author"
3. Enter: "Andrew Ng"
4. Years: 2015-2023
5. Click "Analyze Publications"
6. Wait ~20 seconds
7. View results with AI insights!

Example 2: Bulk Analysis (CSV)

1. Prepare CSV with columns: Name, Affiliation
2. Upload CSV file
3. Set year range
4. Click "Analyze Publications"
5. Get combined analysis for all authors

---

🎨 UI Preview

Input Page

• Clean gradient background (purple/blue)
• Three input methods (tabs)
• Advanced filters (expandable)
• Modern form with hover effects

Results Page

Top: 5 metric cards (Total Pubs, H-Index, i10-Index, Impact, High Impact %)

Left Column: Data preview with filterable table + downloads

Right Column: AI analysis with 4 tabs:

1. 🎯 Impact Analysis
2. 📈 Trend Analysis
3. 💡 Strategic Insights
4. 📊 Visualizations

---

📥 Export Formats

1. Excel (.xlsx) - All publications, multiple sheets
2. Word (.docx) - Formatted report with abstracts
3. JSON (Full) - Complete data + AI evaluation
4. JSON (AI) - Just AI insights

---

🐛 Troubleshooting

"Cannot connect to API"

# Make sure Flask is running
cd API
python main.py

"No publications found"

• Check author name spelling
• Try wider year range
• Add affiliation filter

Slow loading

• Normal! Takes 20-30 seconds
• Fetching from 3 APIs + AI analysis
• Progress bar shows status

---

🎓 Academic Metrics

H-Index

Number of papers (h) with at least h citations each.

• High: 20+ (very impactful)

i10-Index

Number of publications with 10+ citations.

• High: 40+ (productive + impactful)

Impact Score

ML-predicted impact (0-100+) based on 25+ features

---

🎉 Complete Feature List

✅ Multi-source data fetching (3 APIs)
✅ Automatic AI evaluation
✅ Impact prediction (ML)
✅ Trend analysis (NLP + Stats)
✅ H-index & i10-index
✅ Strategic recommendations
✅ Beautiful modern UI
✅ Split-screen results
✅ Interactive charts
✅ Multiple input methods
✅ Excel/Word/JSON export

---

🌟 Status: PRODUCTION READY

To Start:

# Option 1: Double-click (Windows)
START_APP.bat

# Option 2: Manual
# Terminal 1: cd API && python main.py
# Terminal 2: streamlit run streamlit_app.py

---

📞 Documentation

• STREAMLIT_GUIDE.md - Frontend guide
• API/AI_ML_FEATURES.md - AI features (800+ lines)
• API/AUTOMATIC_AI_EVALUATION.md - Auto-eval guide

---

Made with ❤️ using Flask, Streamlit, and Machine Learning