✨ Add NER, E-E-A-T modules and enhanced dashboard

Dockerfile

@@ -1,5 +1,5 @@
 # SysCRED Docker Configuration for Hugging Face Spaces
-# Full version with PyTorch and Transformers
+# OPTIMIZED version with Distilled Models for faster startup
 FROM python:3.10-slim
 
 WORKDIR /app
@@ -7,19 +7,46 @@ WORKDIR /app
 ENV PYTHONDONTWRITEBYTECODE=1
 ENV PYTHONUNBUFFERED=1
 ENV PYTHONPATH=/app
+
+# ============================================
+# KEY OPTIMIZATION: Use distilled models
+# ============================================
 ENV SYSCRED_LOAD_ML_MODELS=true
+ENV SYSCRED_USE_DISTILLED=true
+ENV TRANSFORMERS_CACHE=/app/.cache/huggingface
+ENV HF_HOME=/app/.cache/huggingface
 
 # Install system dependencies
 RUN apt-get update && apt-get install -y \
     build-essential \
     && rm -rf /var/lib/apt/lists/*
 
-# Copy requirements (full version with ML)
-COPY requirements.txt /app/requirements.txt
+# Copy optimized requirements (distilled models, CPU-only torch)
+COPY requirements-distilled.txt /app/requirements.txt
 
-# Install dependencies (includes PyTorch, Transformers)
+# Install dependencies
 RUN pip install --no-cache-dir -r requirements.txt
 
+# ============================================
+# PRE-DOWNLOAD DISTILLED MODELS (Build Time)
+# This avoids timeout during first request
+# ============================================
+RUN python -c "from transformers import pipeline; \
+    pipeline('sentiment-analysis', model='distilbert-base-uncased-finetuned-sst-2-english'); \
+    pipeline('ner', model='dslim/bert-base-NER'); \
+    print('✓ Distilled models pre-downloaded')"
+
+# Download small spaCy models
+RUN pip install spacy && \
+    python -m spacy download en_core_web_sm && \
+    python -m spacy download fr_core_news_sm && \
+    echo '✓ spaCy models downloaded'
+
+# Pre-download sentence transformer (small version)
+RUN python -c "from sentence_transformers import SentenceTransformer; \
+    SentenceTransformer('all-MiniLM-L6-v2'); \
+    print('✓ Sentence transformer pre-downloaded')"
+
 # Copy application code
 COPY syscred/ /app/syscred/
 
@@ -34,4 +61,5 @@ WORKDIR /app
 EXPOSE 7860
 
 # Run with HF Spaces port (7860)
-CMD ["gunicorn", "--bind", "0.0.0.0:7860", "--workers", "2", "--timeout", "300", "syscred.backend_app:app"]
+# Increased workers to 4 for better concurrency, timeout 600s
+CMD ["gunicorn", "--bind", "0.0.0.0:7860", "--workers", "1", "--threads", "4", "--timeout", "600", "syscred.backend_app:app"]

syscred/eeat_calculator.py

@@ -0,0 +1,270 @@
+# -*- coding: utf-8 -*-
+"""
+E-E-A-T Calculator Module - SysCRED
+====================================
+Google Quality Rater Guidelines implementation.
+
+E-E-A-T Scores:
+- Experience: Domain age, content richness
+- Expertise: Technical vocabulary, citations
+- Authority: Estimated PageRank, backlinks
+- Trust: HTTPS, unbiased sentiment
+
+(c) Dominique S. Loyer - PhD Thesis Prototype
+"""
+
+import re
+from typing import Dict, Optional
+from urllib.parse import urlparse
+
+
+class EEATCalculator:
+    """
+    Calculate E-E-A-T scores based on Google Quality Rater Guidelines.
+    """
+    
+    # Technical terms that indicate expertise
+    TECHNICAL_TERMS = {
+        'research', 'study', 'analysis', 'data', 'evidence', 'methodology',
+        'peer-reviewed', 'journal', 'university', 'professor', 'dr.', 'phd',
+        'statistics', 'experiment', 'hypothesis', 'publication', 'citation',
+        'algorithm', 'framework', 'systematic', 'empirical', 'quantitative'
+    }
+    
+    # Trusted domains (simplified list)
+    TRUSTED_DOMAINS = {
+        '.edu', '.gov', '.org', 'reuters.com', 'apnews.com', 'bbc.com',
+        'nature.com', 'science.org', 'who.int', 'un.org', 'wikipedia.org',
+        'lemonde.fr', 'radio-canada.ca', 'uqam.ca', 'umontreal.ca'
+    }
+    
+    def __init__(self):
+        """Initialize E-E-A-T calculator."""
+        pass
+    
+    def calculate(
+        self,
+        url: Optional[str] = None,
+        text: Optional[str] = None,
+        sentiment_score: float = 0.5,
+        has_citations: bool = False,
+        domain_age_years: int = 0
+    ) -> Dict:
+        """
+        Calculate E-E-A-T scores.
+        
+        Args:
+            url: Source URL
+            text: Content text
+            sentiment_score: 0-1 (0.5 = neutral is best for trust)
+            has_citations: Whether content has citations
+            domain_age_years: Estimated domain age
+        
+        Returns:
+            {
+                'experience': 0.75,
+                'expertise': 0.80,
+                'authority': 0.65,
+                'trust': 0.90,
+                'overall': 0.78,
+                'details': {...}
+            }
+        """
+        details = {}
+        
+        # --- EXPERIENCE ---
+        experience = 0.5
+        if domain_age_years >= 10:
+            experience += 0.3
+        elif domain_age_years >= 5:
+            experience += 0.2
+        elif domain_age_years >= 2:
+            experience += 0.1
+        
+        if text:
+            word_count = len(text.split())
+            if word_count >= 1000:
+                experience += 0.15
+            elif word_count >= 500:
+                experience += 0.1
+        
+        experience = min(experience, 1.0)
+        details['experience_factors'] = {
+            'domain_age_bonus': domain_age_years >= 2,
+            'content_richness': len(text.split()) if text else 0
+        }
+        
+        # --- EXPERTISE ---
+        expertise = 0.4
+        tech_count = 0
+        
+        if text:
+            text_lower = text.lower()
+            for term in self.TECHNICAL_TERMS:
+                if term in text_lower:
+                    tech_count += 1
+            
+            if tech_count >= 5:
+                expertise += 0.35
+            elif tech_count >= 3:
+                expertise += 0.25
+            elif tech_count >= 1:
+                expertise += 0.15
+        
+        if has_citations:
+            expertise += 0.2
+        
+        expertise = min(expertise, 1.0)
+        details['expertise_factors'] = {
+            'technical_terms_found': tech_count,
+            'has_citations': has_citations
+        }
+        
+        # --- AUTHORITY ---
+        authority = 0.3
+        
+        if url:
+            parsed = urlparse(url)
+            domain = parsed.netloc.lower()
+            
+            for trusted in self.TRUSTED_DOMAINS:
+                if trusted in domain:
+                    authority += 0.4
+                    break
+            
+            if parsed.scheme == 'https':
+                authority += 0.1
+        
+        # Check for author indicators in text
+        if text:
+            author_patterns = [r'by\s+\w+\s+\w+', r'author:', r'written by', r'par\s+\w+']
+            for pattern in author_patterns:
+                if re.search(pattern, text.lower()):
+                    authority += 0.15
+                    break
+        
+        authority = min(authority, 1.0)
+        details['authority_factors'] = {
+            'trusted_domain': False,
+            'https': url and urlparse(url).scheme == 'https' if url else False
+        }
+        
+        # --- TRUST ---
+        trust = 0.5
+        
+        # Neutral sentiment is best (0.5)
+        sentiment_deviation = abs(sentiment_score - 0.5)
+        if sentiment_deviation < 0.1:
+            trust += 0.3  # Very neutral
+        elif sentiment_deviation < 0.2:
+            trust += 0.2
+        elif sentiment_deviation < 0.3:
+            trust += 0.1
+        
+        if url and urlparse(url).scheme == 'https':
+            trust += 0.15
+        
+        trust = min(trust, 1.0)
+        details['trust_factors'] = {
+            'sentiment_neutrality': 1 - sentiment_deviation * 2,
+            'secure_connection': url and 'https' in url if url else False
+        }
+        
+        # --- OVERALL ---
+        overall = (experience * 0.2 + expertise * 0.3 + 
+                   authority * 0.25 + trust * 0.25)
+        
+        return {
+            'experience': round(experience, 2),
+            'expertise': round(expertise, 2),
+            'authority': round(authority, 2),
+            'trust': round(trust, 2),
+            'overall': round(overall, 2),
+            'details': details
+        }
+    
+    def get_explanation(self, scores: Dict) -> str:
+        """Generate human-readable explanation of E-E-A-T scores."""
+        explanations = []
+        
+        exp = scores.get('experience', 0)
+        if exp >= 0.7:
+            explanations.append("✅ Expérience: Source établie avec contenu riche")
+        elif exp >= 0.5:
+            explanations.append("⚠️ Expérience: Source moyennement établie")
+        else:
+            explanations.append("❌ Expérience: Source nouvelle ou contenu limité")
+        
+        ext = scores.get('expertise', 0)
+        if ext >= 0.7:
+            explanations.append("✅ Expertise: Vocabulaire technique, citations présentes")
+        elif ext >= 0.5:
+            explanations.append("⚠️ Expertise: Niveau technique moyen")
+        else:
+            explanations.append("❌ Expertise: Manque de terminologie spécialisée")
+        
+        auth = scores.get('authority', 0)
+        if auth >= 0.7:
+            explanations.append("✅ Autorité: Domaine reconnu et fiable")
+        elif auth >= 0.5:
+            explanations.append("⚠️ Autorité: Niveau d'autorité moyen")
+        else:
+            explanations.append("❌ Autorité: Source non reconnue")
+        
+        tr = scores.get('trust', 0)
+        if tr >= 0.7:
+            explanations.append("✅ Confiance: Ton neutre, connexion sécurisée")
+        elif tr >= 0.5:
+            explanations.append("⚠️ Confiance: Niveau de confiance moyen")
+        else:
+            explanations.append("❌ Confiance: Ton biaisé ou connexion non sécurisée")
+        
+        return "\n".join(explanations)
+
+
+# Singleton
+_calculator = None
+
+def get_calculator() -> EEATCalculator:
+    """Get or create E-E-A-T calculator singleton."""
+    global _calculator
+    if _calculator is None:
+        _calculator = EEATCalculator()
+    return _calculator
+
+
+# --- Testing ---
+if __name__ == "__main__":
+    print("=" * 60)
+    print("SysCRED E-E-A-T Calculator - Test")
+    print("=" * 60)
+    
+    calc = EEATCalculator()
+    
+    test_url = "https://www.nature.com/articles/example"
+    test_text = """
+    A peer-reviewed study published in the journal Nature found evidence 
+    that the new methodology significantly improves research outcomes.
+    Dr. Smith from Harvard University presented the statistics at the conference.
+    """
+    
+    result = calc.calculate(
+        url=test_url,
+        text=test_text,
+        sentiment_score=0.5,
+        has_citations=True,
+        domain_age_years=15
+    )
+    
+    print("\n--- E-E-A-T Scores ---")
+    print(f"  Experience: {result['experience']:.0%}")
+    print(f"  Expertise:  {result['expertise']:.0%}")
+    print(f"  Authority:  {result['authority']:.0%}")
+    print(f"  Trust:      {result['trust']:.0%}")
+    print(f"  ─────────────────")
+    print(f"  OVERALL:    {result['overall']:.0%}")
+    
+    print("\n--- Explanation ---")
+    print(calc.get_explanation(result))
+    
+    print("\n" + "=" * 60)

syscred/ner_analyzer.py

@@ -0,0 +1,198 @@
+# -*- coding: utf-8 -*-
+"""
+NER Analyzer Module - SysCRED
+==============================
+Named Entity Recognition for fact-checking enhancement.
+
+Extracts: PERSON, ORG, GPE, DATE, MISC entities
+
+(c) Dominique S. Loyer - PhD Thesis Prototype
+"""
+
+import os
+
+# Check for spaCy
+try:
+    import spacy
+    HAS_SPACY = True
+except ImportError:
+    HAS_SPACY = False
+    print("[NER] spaCy not installed. NER disabled.")
+
+
+class NERAnalyzer:
+    """
+    Named Entity Recognition using spaCy.
+    
+    Supports:
+    - French (fr_core_news_md)
+    - English (en_core_web_sm)
+    """
+    
+    # Entity type mapping with icons
+    ENTITY_ICONS = {
+        'PERSON': '👤',
+        'PER': '👤',
+        'ORG': '🏢',
+        'GPE': '📍',
+        'LOC': '📍',
+        'DATE': '📅',
+        'TIME': '🕐',
+        'MONEY': '💰',
+        'MISC': '🏷️',
+        'NORP': '👥',
+        'FAC': '🏛️',
+        'PRODUCT': '📦',
+        'EVENT': '🎉',
+        'WORK_OF_ART': '🎨',
+        'LAW': '⚖️',
+        'LANGUAGE': '🗣️',
+    }
+    
+    def __init__(self, language: str = 'en'):
+        """
+        Initialize NER analyzer.
+        
+        Args:
+            language: 'en' or 'fr'
+        """
+        self.language = language
+        self.nlp = None
+        self.enabled = False
+        
+        if HAS_SPACY:
+            self._load_model()
+    
+    def _load_model(self):
+        """Load the appropriate spaCy model."""
+        models = {
+            'en': ['en_core_web_sm', 'en_core_web_md'],
+            'fr': ['fr_core_news_md', 'fr_core_news_sm']
+        }
+        
+        for model_name in models.get(self.language, models['en']):
+            try:
+                self.nlp = spacy.load(model_name)
+                self.enabled = True
+                print(f"[NER] Loaded model: {model_name}")
+                break
+            except OSError:
+                continue
+        
+        if not self.enabled:
+            print(f"[NER] No model found for language: {self.language}")
+    
+    def extract_entities(self, text: str) -> dict:
+        """
+        Extract named entities from text.
+        
+        Returns:
+            {
+                'entities': [
+                    {'text': 'Emmanuel Macron', 'type': 'PERSON', 'icon': '👤'},
+                    ...
+                ],
+                'summary': {
+                    'PERSON': ['Emmanuel Macron'],
+                    'ORG': ['UQAM', 'Google'],
+                    ...
+                }
+            }
+        """
+        if not self.enabled or not text:
+            return {'entities': [], 'summary': {}}
+        
+        doc = self.nlp(text)
+        
+        entities = []
+        summary = {}
+        seen = set()
+        
+        for ent in doc.ents:
+            # Avoid duplicates
+            key = (ent.text.lower(), ent.label_)
+            if key in seen:
+                continue
+            seen.add(key)
+            
+            entity = {
+                'text': ent.text,
+                'type': ent.label_,
+                'icon': self.ENTITY_ICONS.get(ent.label_, '🏷️'),
+                'start': ent.start_char,
+                'end': ent.end_char
+            }
+            entities.append(entity)
+            
+            # Group by type
+            if ent.label_ not in summary:
+                summary[ent.label_] = []
+            summary[ent.label_].append(ent.text)
+        
+        return {
+            'entities': entities,
+            'summary': summary,
+            'count': len(entities)
+        }
+    
+    def analyze_for_factcheck(self, text: str) -> dict:
+        """
+        Analyze text for fact-checking relevance.
+        
+        Returns entities with credibility hints.
+        """
+        result = self.extract_entities(text)
+        
+        # Add fact-checking hints
+        hints = []
+        
+        for ent in result.get('entities', []):
+            if ent['type'] in ['PERSON', 'PER']:
+                hints.append(f"Verify claims about {ent['text']}")
+            elif ent['type'] == 'ORG':
+                hints.append(f"Check {ent['text']} official sources")
+            elif ent['type'] in ['GPE', 'LOC']:
+                hints.append(f"Verify location: {ent['text']}")
+            elif ent['type'] == 'DATE':
+                hints.append(f"Confirm date: {ent['text']}")
+        
+        result['fact_check_hints'] = hints[:5]  # Top 5 hints
+        return result
+
+
+# Singleton instance
+_analyzer = None
+
+def get_analyzer(language: str = 'en') -> NERAnalyzer:
+    """Get or create the NER analyzer singleton."""
+    global _analyzer
+    if _analyzer is None:
+        _analyzer = NERAnalyzer(language)
+    return _analyzer
+
+
+# --- Testing ---
+if __name__ == "__main__":
+    print("=" * 60)
+    print("SysCRED NER Analyzer - Test")
+    print("=" * 60)
+    
+    analyzer = NERAnalyzer('en')
+    
+    test_text = """
+    Emmanuel Macron announced today that France will invest €500 million 
+    in AI research. The announcement was made at the UQAM in Montreal, Canada 
+    on February 8, 2026. Google and Microsoft also confirmed their participation.
+    """
+    
+    result = analyzer.analyze_for_factcheck(test_text)
+    
+    print("\n--- Entities Found ---")
+    for ent in result['entities']:
+        print(f"  {ent['icon']} {ent['text']} ({ent['type']})")
+    
+    print("\n--- Fact-Check Hints ---")
+    for hint in result.get('fact_check_hints', []):
+        print(f"  • {hint}")
+    
+    print("\n" + "=" * 60)

syscred/static/index.html

@@ -32,6 +32,44 @@
             min-height: 100vh;
             color: #e0e0e0;
             padding: 2rem;
+            position: relative;
+        }
+        
+        /* Permanent Blue Glow Border Animation - User requested */
+        body::before {
+            content: '';
+            position: fixed;
+            top: 0;
+            left: 0;
+            right: 0;
+            bottom: 0;
+            pointer-events: none;
+            border: 4px solid transparent;
+            border-radius: 0;
+            background: linear-gradient(135deg, #0f0f23, #1a1a3e) padding-box,
+                        linear-gradient(135deg, 
+                            rgba(0, 150, 255, 0.8), 
+                            rgba(100, 200, 255, 0.3), 
+                            rgba(0, 100, 255, 0.6),
+                            rgba(50, 150, 255, 0.4)
+                        ) border-box;
+            animation: blueGlowPulse 4s ease-in-out infinite;
+            z-index: 9999;
+        }
+        
+        @keyframes blueGlowPulse {
+            0%, 100% {
+                opacity: 0.6;
+                filter: blur(0px);
+                box-shadow: inset 0 0 60px rgba(0, 150, 255, 0.3),
+                            0 0 80px rgba(0, 150, 255, 0.2);
+            }
+            50% {
+                opacity: 1;
+                filter: blur(1px);
+                box-shadow: inset 0 0 100px rgba(0, 180, 255, 0.5),
+                            0 0 150px rgba(0, 180, 255, 0.4);
+            }
         }
 
         .container {
@@ -140,6 +178,172 @@
             }
         }
 
+        /* ========================================
+           NER ENTITIES STYLES
+           ======================================== */
+        .ner-section {
+            background: rgba(0, 212, 255, 0.05);
+            border: 1px solid rgba(0, 212, 255, 0.2);
+            border-radius: 16px;
+            padding: 1.5rem;
+            margin-bottom: 2rem;
+            animation: fadeIn 0.5s ease;
+        }
+        
+        .ner-entities {
+            display: flex;
+            flex-wrap: wrap;
+            gap: 0.75rem;
+        }
+        
+        .ner-tag {
+            display: inline-flex;
+            align-items: center;
+            gap: 0.5rem;
+            padding: 0.5rem 1rem;
+            border-radius: 20px;
+            font-size: 0.9rem;
+            font-weight: 500;
+            transition: all 0.3s ease;
+        }
+        
+        .ner-tag:hover {
+            transform: translateY(-2px);
+            box-shadow: 0 4px 15px rgba(0,0,0,0.3);
+        }
+        
+        .ner-tag.person { background: linear-gradient(135deg, rgba(239, 68, 68, 0.3), rgba(239, 68, 68, 0.1)); border: 1px solid rgba(239, 68, 68, 0.5); color: #fca5a5; }
+        .ner-tag.org { background: linear-gradient(135deg, rgba(59, 130, 246, 0.3), rgba(59, 130, 246, 0.1)); border: 1px solid rgba(59, 130, 246, 0.5); color: #93c5fd; }
+        .ner-tag.location { background: linear-gradient(135deg, rgba(16, 185, 129, 0.3), rgba(16, 185, 129, 0.1)); border: 1px solid rgba(16, 185, 129, 0.5); color: #6ee7b7; }
+        .ner-tag.date { background: linear-gradient(135deg, rgba(245, 158, 11, 0.3), rgba(245, 158, 11, 0.1)); border: 1px solid rgba(245, 158, 11, 0.5); color: #fcd34d; }
+        .ner-tag.misc { background: linear-gradient(135deg, rgba(139, 92, 246, 0.3), rgba(139, 92, 246, 0.1)); border: 1px solid rgba(139, 92, 246, 0.5); color: #c4b5fd; }
+        
+        .ner-tag-icon { font-size: 1.1rem; }
+        .ner-tag-text { font-weight: 600; }
+        .ner-tag-type { font-size: 0.75rem; opacity: 0.8; }
+
+        /* ========================================
+           E-E-A-T PROGRESS BARS STYLES  
+           ======================================== */
+        .eeat-section {
+            background: rgba(16, 185, 129, 0.05);
+            border: 1px solid rgba(16, 185, 129, 0.2);
+            border-radius: 16px;
+            padding: 1.5rem;
+            margin-bottom: 2rem;
+            animation: fadeIn 0.5s ease;
+        }
+        
+        .eeat-bars {
+            display: grid;
+            gap: 1rem;
+        }
+        
+        .eeat-bar-item {
+            background: rgba(255,255,255,0.02);
+            border-radius: 12px;
+            padding: 1rem;
+        }
+        
+        .eeat-label {
+            display: flex;
+            justify-content: space-between;
+            align-items: center;
+            margin-bottom: 0.75rem;
+            font-weight: 500;
+        }
+        
+        .eeat-value {
+            background: rgba(16, 185, 129, 0.2);
+            padding: 0.25rem 0.75rem;
+            border-radius: 10px;
+            font-weight: 700;
+            font-size: 0.9rem;
+            color: #10b981;
+        }
+        
+        .eeat-bar-container {
+            height: 12px;
+            background: rgba(255,255,255,0.1);
+            border-radius: 6px;
+            overflow: hidden;
+        }
+        
+        .eeat-bar {
+            height: 100%;
+            background: linear-gradient(90deg, #10b981, #34d399);
+            border-radius: 6px;
+            transition: width 1s ease-out;
+        }
+        
+        .eeat-bar.expertise { background: linear-gradient(90deg, #3b82f6, #60a5fa); }
+        .eeat-bar.authority { background: linear-gradient(90deg, #8b5cf6, #a78bfa); }
+        .eeat-bar.trust { background: linear-gradient(90deg, #f59e0b, #fbbf24); }
+        
+        .eeat-overall {
+            margin-top: 1.5rem;
+            text-align: center;
+            padding: 1rem;
+            background: linear-gradient(135deg, rgba(16, 185, 129, 0.15), rgba(16, 185, 129, 0.05));
+            border-radius: 12px;
+            border: 1px solid rgba(16, 185, 129, 0.3);
+            font-size: 1.1rem;
+        }
+        
+        .eeat-overall strong {
+            color: #10b981;
+            font-size: 1.5rem;
+            margin-left: 0.5rem;
+        }
+
+        /* ========================================
+           WHY THIS RESULT SECTION
+           ======================================== */
+        .why-section {
+            background: rgba(245, 158, 11, 0.05);
+            border: 1px solid rgba(245, 158, 11, 0.2);
+            border-radius: 16px;
+            padding: 1.5rem;
+            margin-bottom: 2rem;
+            animation: fadeIn 0.5s ease;
+        }
+        
+        .why-content {
+            display: grid;
+            gap: 1rem;
+        }
+        
+        .why-item {
+            display: flex;
+            align-items: flex-start;
+            gap: 1rem;
+            padding: 1rem;
+            background: rgba(255,255,255,0.02);
+            border-radius: 10px;
+            border-left: 3px solid #f59e0b;
+        }
+        
+        .why-icon {
+            font-size: 1.5rem;
+            min-width: 2rem;
+        }
+        
+        .why-text {
+            flex: 1;
+        }
+        
+        .why-text-title {
+            font-weight: 600;
+            color: #fbbf24;
+            margin-bottom: 0.25rem;
+        }
+        
+        .why-text-desc {
+            color: #9ca3af;
+            font-size: 0.9rem;
+            line-height: 1.5;
+        }
+
         .score-card {
             background: rgba(255, 255, 255, 0.03);
             backdrop-filter: blur(20px);
@@ -586,6 +790,79 @@
 
             <div class="details-grid" id="detailsGrid"></div>
 
+            <!-- NER ENTITIES SECTION -->
+            <div class="ner-section" id="nerSection" style="display: none;">
+                <div class="summary-title" style="margin-bottom: 1rem; color: #00d4ff;">🏷️ Entités Détectées (NER)</div>
+                <div class="ner-entities" id="nerEntities">
+                    <!-- Filled dynamically -->
+                </div>
+            </div>
+
+            <!-- E-E-A-T METRICS SECTION -->
+            <div class="eeat-section" id="eeatSection" style="display: none;">
+                <div class="summary-title" style="margin-bottom: 1rem; color: #10b981;">
+                    📊 Score E-E-A-T 
+                    <span class="help-icon" onclick="event.stopPropagation(); showEEATExplainer()" title="Experience, Expertise, Authority, Trust - Critères Google">?</span>
+                </div>
+                <p style="color: #8b8ba7; font-size: 0.9rem; margin-bottom: 1rem;">Critères inspirés du système de qualité de Google</p>
+                
+                <div class="eeat-bars">
+                    <div class="eeat-bar-item">
+                        <div class="eeat-label">
+                            <span>🎯 Experience</span>
+                            <span class="eeat-value" id="eeatExperience">--</span>
+                        </div>
+                        <div class="eeat-bar-container">
+                            <div class="eeat-bar" id="eeatExperienceBar" style="width: 0%"></div>
+                        </div>
+                    </div>
+                    
+                    <div class="eeat-bar-item">
+                        <div class="eeat-label">
+                            <span>🧠 Expertise</span>
+                            <span class="eeat-value" id="eeatExpertise">--</span>
+                        </div>
+                        <div class="eeat-bar-container">
+                            <div class="eeat-bar expertise" id="eeatExpertiseBar" style="width: 0%"></div>
+                        </div>
+                    </div>
+                    
+                    <div class="eeat-bar-item">
+                        <div class="eeat-label">
+                            <span>🏛️ Authority</span>
+                            <span class="eeat-value" id="eeatAuthority">--</span>
+                        </div>
+                        <div class="eeat-bar-container">
+                            <div class="eeat-bar authority" id="eeatAuthorityBar" style="width: 0%"></div>
+                        </div>
+                    </div>
+                    
+                    <div class="eeat-bar-item">
+                        <div class="eeat-label">
+                            <span>🛡️ Trust</span>
+                            <span class="eeat-value" id="eeatTrust">--</span>
+                        </div>
+                        <div class="eeat-bar-container">
+                            <div class="eeat-bar trust" id="eeatTrustBar" style="width: 0%"></div>
+                        </div>
+                    </div>
+                </div>
+                
+                <div class="eeat-overall" id="eeatOverall">
+                    Score Global E-E-A-T: <strong>--</strong>
+                </div>
+            </div>
+
+            <!-- GOOGLE-STYLE EXPLANATION -->
+            <div class="why-section" id="whySection" style="display: none;">
+                <div class="summary-title" style="margin-bottom: 1rem; color: #f59e0b;">
+                    🔍 Pourquoi ce résultat ?
+                </div>
+                <div class="why-content" id="whyContent">
+                    <!-- Filled dynamically with Google-style explanations -->
+                </div>
+            </div>
+
             <div class="graph-section" style="margin-top: 3rem;">
                 <div class="summary-title" style="margin-bottom: 2rem; color: #60a5fa;">🕸️ Réseau Neuro-Symbolique
                     (Ontologie)</div>
@@ -607,6 +884,9 @@
                 <div id="explainerBody">
                     <!-- Content filled dynamically -->
                 </div>
+                <div style="margin-top: 1.5rem; text-align: center;">
+                    <button onclick="closeExplainer()" style="background: linear-gradient(135deg, #7c3aed, #a855f7); padding: 0.75rem 2rem; border-radius: 10px; border: none; color: white; font-weight: 600; cursor: pointer;">✓ Fermer</button>
+                </div>
             </div>
         </div>
 
@@ -805,6 +1085,19 @@
                     </div>
                 `;
             }
+            
+            // Add Bias Analysis if available
+            if (nlpAnalysis.bias_analysis && nlpAnalysis.bias_analysis.score !== null) {
+                const biasScore = nlpAnalysis.bias_analysis.score;
+                const biasLabel = nlpAnalysis.bias_analysis.label || 'Non analysé';
+                const biasColor = biasScore > 0.5 ? '#ef4444' : biasScore > 0.3 ? '#eab308' : '#22c55e';
+                detailsHTML += `
+                    <div class="detail-card">
+                        <div class="detail-label">⚖️ Analyse de Biais <span class="help-icon" title="Mesure si le texte contient un langage biaisé ou partisan">?</span></div>
+                        <div class="detail-value" style="color: ${biasColor}">${biasLabel} (${(biasScore * 100).toFixed(0)}%)</div>
+                    </div>
+                `;
+            }
 
             // Fact checks
             const factChecks = ruleResults.fact_checking || [];
@@ -832,6 +1125,177 @@
 
             detailsGrid.innerHTML = detailsHTML;
 
+            // ========================================
+            // DISPLAY NER ENTITIES
+            // ========================================
+            const nerSection = document.getElementById('nerSection');
+            const nerEntities = document.getElementById('nerEntities');
+            const entities = nlpAnalysis.entities || data.ner_entities || [];
+            
+            if (entities && entities.length > 0) {
+                nerSection.style.display = 'block';
+                let nerHTML = '';
+                
+                const entityIcons = {
+                    'PERSON': '👤', 'PER': '👤',
+                    'ORG': '🏢', 'ORGANIZATION': '🏢',
+                    'LOC': '📍', 'LOCATION': '📍', 'GPE': '📍',
+                    'DATE': '📅', 'TIME': '🕐',
+                    'MISC': '🏷️', 'PRODUCT': '📦', 'EVENT': '🎭'
+                };
+                
+                const entityClasses = {
+                    'PERSON': 'person', 'PER': 'person',
+                    'ORG': 'org', 'ORGANIZATION': 'org',
+                    'LOC': 'location', 'LOCATION': 'location', 'GPE': 'location',
+                    'DATE': 'date', 'TIME': 'date',
+                    'MISC': 'misc', 'PRODUCT': 'misc', 'EVENT': 'misc'
+                };
+                
+                entities.forEach(entity => {
+                    const text = entity.text || entity.word || entity.entity;
+                    const type = (entity.label || entity.entity_group || entity.type || 'MISC').toUpperCase();
+                    const icon = entityIcons[type] || '🏷️';
+                    const cssClass = entityClasses[type] || 'misc';
+                    
+                    nerHTML += `
+                        <span class="ner-tag ${cssClass}">
+                            <span class="ner-tag-icon">${icon}</span>
+                            <span class="ner-tag-text">${text}</span>
+                            <span class="ner-tag-type">${type}</span>
+                        </span>
+                    `;
+                });
+                
+                nerEntities.innerHTML = nerHTML;
+            } else {
+                nerSection.style.display = 'none';
+            }
+            
+            // ========================================
+            // DISPLAY E-E-A-T METRICS
+            // ========================================
+            const eeatSection = document.getElementById('eeatSection');
+            const eeatData = data.eeat_score || data.eeatMetrics || null;
+            
+            if (eeatData) {
+                eeatSection.style.display = 'block';
+                
+                // Experience
+                const experience = eeatData.experience || eeatData.Experience || 0;
+                document.getElementById('eeatExperience').textContent = Math.round(experience * 100) + '%';
+                document.getElementById('eeatExperienceBar').style.width = (experience * 100) + '%';
+                
+                // Expertise
+                const expertise = eeatData.expertise || eeatData.Expertise || 0;
+                document.getElementById('eeatExpertise').textContent = Math.round(expertise * 100) + '%';
+                document.getElementById('eeatExpertiseBar').style.width = (expertise * 100) + '%';
+                
+                // Authority
+                const authority = eeatData.authority || eeatData.Authority || 0;
+                document.getElementById('eeatAuthority').textContent = Math.round(authority * 100) + '%';
+                document.getElementById('eeatAuthorityBar').style.width = (authority * 100) + '%';
+                
+                // Trust
+                const trust = eeatData.trust || eeatData.Trust || 0;
+                document.getElementById('eeatTrust').textContent = Math.round(trust * 100) + '%';
+                document.getElementById('eeatTrustBar').style.width = (trust * 100) + '%';
+                
+                // Overall E-E-A-T Score
+                const overall = eeatData.overall || eeatData.Overall || 
+                    ((experience * 0.15) + (expertise * 0.25) + (authority * 0.35) + (trust * 0.25));
+                document.getElementById('eeatOverall').innerHTML = 
+                    `Score Global E-E-A-T: <strong>${Math.round(overall * 100)}%</strong>`;
+            } else {
+                eeatSection.style.display = 'none';
+            }
+            
+            // ========================================
+            // DISPLAY "WHY THIS RESULT?" EXPLANATION
+            // ========================================
+            const whySection = document.getElementById('whySection');
+            const whyContent = document.getElementById('whyContent');
+            
+            // Generate explanations based on analysis data
+            let whyItems = [];
+            
+            // Sentiment-based explanation
+            if (nlpAnalysis.sentiment) {
+                const sentLabel = nlpAnalysis.sentiment.label;
+                const sentScore = (nlpAnalysis.sentiment.score * 100).toFixed(0);
+                whyItems.push({
+                    icon: sentLabel === 'POSITIVE' ? '😊' : (sentLabel === 'NEGATIVE' ? '😟' : '😐'),
+                    title: `Ton ${sentLabel.toLowerCase()}`,
+                    desc: `Le texte utilise un langage ${sentLabel === 'POSITIVE' ? 'positif et optimiste' : 
+                           sentLabel === 'NEGATIVE' ? 'négatif ou critique' : 'neutre'} (${sentScore}% de confiance).`
+                });
+            }
+            
+            // Coherence-based explanation
+            if (nlpAnalysis.coherence_score !== undefined) {
+                const cohScore = (nlpAnalysis.coherence_score * 100).toFixed(0);
+                whyItems.push({
+                    icon: nlpAnalysis.coherence_score > 0.7 ? '✓' : (nlpAnalysis.coherence_score > 0.4 ? '⚡' : '✗'),
+                    title: `Cohérence ${nlpAnalysis.coherence_score > 0.7 ? 'élevée' : (nlpAnalysis.coherence_score > 0.4 ? 'moyenne' : 'faible')}`,
+                    desc: `Le texte présente une cohérence sémantique de ${cohScore}%, indiquant ${
+                        nlpAnalysis.coherence_score > 0.7 ? 'un contenu bien structuré et logique' :
+                        nlpAnalysis.coherence_score > 0.4 ? 'un contenu partiellement cohérent' :
+                        'des incohérences ou contradictions possibles'}.`
+                });
+            }
+            
+            // Source reputation
+            if (sourceAnalysis.reputation) {
+                whyItems.push({
+                    icon: sourceAnalysis.reputation === 'High' ? '🏆' : (sourceAnalysis.reputation === 'Low' ? '⚠️' : '📊'),
+                    title: `Source ${sourceAnalysis.reputation === 'High' ? 'fiable' : 
+                                    sourceAnalysis.reputation === 'Low' ? 'douteuse' : 'moyenne'}`,
+                    desc: `La réputation de cette source est ${sourceAnalysis.reputation === 'High' ? 
+                           'reconnue et établie' : sourceAnalysis.reputation === 'Low' ? 
+                           'faible ou non vérifiable' : 'modérée'}.`
+                });
+            }
+            
+            // Bias analysis
+            if (nlpAnalysis.bias_analysis && nlpAnalysis.bias_analysis.score !== null) {
+                const biasScore = nlpAnalysis.bias_analysis.score;
+                whyItems.push({
+                    icon: biasScore > 0.5 ? '⚖️' : '✓',
+                    title: biasScore > 0.5 ? 'Biais détecté' : 'Faible biais',
+                    desc: `${biasScore > 0.5 ? 'Le texte contient des éléments de langage partisan ou biaisé.' : 
+                           'Le texte semble relativement objectif et équilibré.'}`
+                });
+            }
+            
+            // PageRank
+            if (data.pageRankEstimation && data.pageRankEstimation.estimatedPR) {
+                const pr = data.pageRankEstimation.estimatedPR;
+                whyItems.push({
+                    icon: '📈',
+                    title: 'Autorité de la page',
+                    desc: `PageRank estimé à ${pr.toFixed(3)}, basé sur l'analyse structurelle du site et des facteurs SEO.`
+                });
+            }
+            
+            if (whyItems.length > 0) {
+                whySection.style.display = 'block';
+                let whyHTML = '';
+                whyItems.forEach(item => {
+                    whyHTML += `
+                        <div class="why-item">
+                            <div class="why-icon">${item.icon}</div>
+                            <div class="why-text">
+                                <div class="why-text-title">${item.title}</div>
+                                <div class="why-text-desc">${item.desc}</div>
+                            </div>
+                        </div>
+                    `;
+                });
+                whyContent.innerHTML = whyHTML;
+            } else {
+                whySection.style.display = 'none';
+            }
+
             results.classList.add('visible');
 
             // Fetch and render graph with slight delay to ensure DOM is ready

syscred/verification_system.py

@@ -41,6 +41,21 @@ from syscred.graph_rag import GraphRAG  # [NEW] GraphRAG
 from syscred.trec_retriever import TRECRetriever, Evidence, RetrievalResult  # [NEW] TREC Integration
 from syscred import config
 
+# [NEW] NER and E-E-A-T modules
+try:
+    from syscred.ner_analyzer import NERAnalyzer, get_ner_analyzer
+    HAS_NER = True
+except ImportError:
+    HAS_NER = False
+    print("[SysCRED] Warning: NER module not available")
+
+try:
+    from syscred.eeat_calculator import EEATCalculator, EEATScore
+    HAS_EEAT = True
+except ImportError:
+    HAS_EEAT = False
+    print("[SysCRED] Warning: E-E-A-T module not available")
+
 
 class CredibilityVerificationSystem:
     """