trust-sense 0.1.1

Advanced Multimodal AI Library for Fake News & Psyops Detection

Trust Sense

Advanced Multimodal AI Library for Fake News & Psyops Detection

A powerful Python library for detecting fake news, psychological operations, propaganda, and manipulated media.

🚀 Quick Start

from trust_sense import detect_fake_news, detect_psyops

# Detect fake news
is_fake = detect_fake_news("Breaking: Scientists discover cure for aging!")
print(f"Fake news detected: {is_fake}")

# Detect psyops/manipulation
is_psyops = detect_psyops("URGENT!!! SHARE THIS NOW OR YOU'LL REGRET IT!!!")
print(f"Psyops detected: {is_psyops}")

📦 Installation

# Basic installation
pip install trust-sense

# Full features with ML models
pip install trust-sense[full]

# API server support
pip install trust-sense[api]

# Development tools
pip install trust-sense[dev]

🎯 Features

• Text Analysis: Detect fake news, manipulation, and propaganda
• Audio Analysis: Emotion detection and credibility assessment
• Video Analysis: Deepfake detection and facial analysis
• Multimodal: Combined analysis across multiple data types
• Lazy Loading: Optional dependencies loaded only when needed
• Graceful Fallback: Works without heavy ML models

💡 Usage Examples

Quick Detection Functions

from trust_sense import detect_fake_news, detect_psyops, analyze_trust

# Simple fake news detection
is_fake = detect_fake_news("Breaking: UFO lands in Times Square!")

# Psychological operations detection
is_psyops = detect_psyops("SHARE THIS OR THEY'LL HIDE THE TRUTH!!!")

# Comprehensive analysis
analysis = analyze_trust("Some suspicious content...")
print(f"Risk Level: {analysis['risk_level']}")

Advanced Usage with Detector Classes

from trust_sense import FakeNewsDetector, PsyopsDetector, TrustAnalyzer

# Fake news detector
detector = FakeNewsDetector()
result = detector.analyze("Article text...")
print(f"Confidence: {result.confidence:.2%}")
print(f"Risk Level: {result.risk_level}")

# Psyops detector
psyops = PsyopsDetector()
result = psyops.analyze("Manipulative content...")
print(f"Techniques: {result.techniques}")

API Server

from trust_sense import TrustAPI

# Start API server
api = TrustAPI(host='0.0.0.0', port=8000)
api.run()

# Visit: http://localhost:8000/docs for interactive API docs

📚 Documentation

For detailed API reference and advanced usage, see:

• Package documentation in docs/trust_sense_documentation.tex (LaTeX source)
• Examples in trust_sense/examples/ directory
• API server documentation at http://localhost:8000/docs when running the server

🧪 Testing

# Install development dependencies
pip install trust-sense[dev]

# Run tests
pytest

# Run with coverage
pytest --cov=trust_sense

🤝 Contributing

Contributions are welcome! Please:

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Add tests
5. Submit a pull request

📄 License

MIT License - see LICENSE file

�‍💻 Author

Created by Codisa

�📞 Support

• Issues: https://github.com/codisia/trust-sense/issues
• Email: [e-mail]
• Documentation: https://github.com/codisia/trust-sense#readme

---

Version: 0.1.0
Python: >= 3.8