Applied Research

AI-Driven Data Science & Counterterrorism

Computational analysis of extremist discourse and ideological transmission using machine learning, natural language processing, and network analysis.

Network co-occurrence analysis revealing conceptual architecture

Parallel Critiques: Analyzing Rhetorical Extremism

Rigorous NLP analysis of textual and conceptual overlap between academic discourse and extremist frameworks, revealing transformation points from abstract critique to concrete threat identification.

📚 Read the Full Analysis at scideology.app →

Key Findings

16% semantic similarity, 75% conceptual overlap identified between discourse patterns
Network density analysis: 3x difference between abstract vs operationalized ideologies
Mapped implicit terminology frameworks showing how shared vocabulary masks fundamentally different conceptual architectures
Interactive analysis dashboards with comprehensive visualization tools in Jupyter notebooks

Technical Stack

Python scikit-learn NetworkX TF-IDF N-gram Analysis Network Co-occurrence

Methodology

→ TF-IDF vectorization
→ Network co-occurrence mapping
→ Semantic similarity analysis
→ Thematic clustering

Status

Manuscript in Preparation
Technical monograph with full methodology and findings

Applications

This research compares Jordan Peterson's PragerU propaganda to Nazi Anders Breivik's extremism—both use psychological manipulation to pretend play their imagined heroism.