🌐 MAJOR UPDATE: National Security and Defence Documents Dataset (1987-2024) v2.0
I'm excited to announce the release of version 2.0 of our comprehensive dataset on global security and defence policies! 📊
I'm excited to announce the release of version 2.0 of our comprehensive dataset on global security and defence policies! 📊
Comments
🔄 Expanded corpus: Added 32 new documents from 6 additional countries
🔍 Improved search tools: Refined semantic search capabilities with higher accuracy
🧠 Advanced NLP techniques: Updated encoding models and analysis tools
🔄 Increased reproducibility: Complete code for all computational text analysis steps
A collection of 607 national security documents from 119 countries spanning nearly four decades (1987-2024), including national security strategies, defence white papers and top-level security policies.
This dataset enables researchers to:
- Conduct cross-national comparative analyses of security priorities
- Track the evolution of security concepts over time
- Identify regional patterns in defence planning
- Analyse how different countries conceptualise threats
- Machine-readable PDFs and txt files with OCR processing
- Non-English documents accompanied by translations
- Comprehensive metadata including UN region, regime type, and economic data
- Semantic search functionality using Google's Universal Sentence Encoder
- Jupyter notebooks for data exploration and visualisation
- Reproducible code for computational text analysis