🤖 AI Summary
This study addresses the challenges posed by fragmented and heterogeneous data in child sexual exploitation and abuse (CSEA) cases, which hinder cross-case analysis and impose significant emotional burdens on investigators. To overcome these issues, the authors propose a modular open-source system that combines regular expressions with semantic pattern analysis to enable interpretable and auditable extraction of structured information, thereby constructing a unified case data model. The system employs a multidimensional weighted Jaccard similarity measure for case clustering and integrates six types of interactive visualizations—including timelines and severity indicators—to support automated triage and in-depth investigative reasoning. Evaluation on 47 AZICAC reports (2011–2014) demonstrates that the system substantially improves cross-case analytical efficiency and effectively reduces the manual handling of sensitive content.
📝 Abstract
Child sexual exploitation and abuse (CSEA) case data is inherently disturbing, fragmented across multiple organizations, jurisdictions, and agencies, with varying levels of detail and formatting, making cross-case analysis, pattern identification, and trend detection challenging. This paper presents CaseLinker, a modular system for ingesting, processing, analyzing, and visualizing CSEA case data. CaseLinker employs a hybrid deterministic information extraction approach combining regex-based extraction for structured data (demographics, platforms, evidence) with pattern-based semantic analysis for severity indicators and case topics, ensuring interpretability and auditability. The system extracts relevant case information, populates a comprehensive case schema, creates six interactive visualizations (Timeline, Severity Indicators, Case Visualization, Previous Perpetrator Status, Environment/Platforms, Organizations Involved), provides a platform for deeper automated and manual analysis, groups similar cases using weighted Jaccard similarity across multiple dimensions (platforms, demographics, topics, severity, investigation type), and provides automated triage and insights based on collected case data. CaseLinker is evaluated on 47 cases from publicly available AZICAC reports (2011-2014), demonstrating effective information extraction, case clustering, automated insights generation, and interactive visualization capabilities. CaseLinker addresses critical challenges in case analysis including fragmented data sources, cross-case pattern identification, and the emotional burden of repeatedly processing disturbing case material.