Interactive Discovery of Coordinated Relationship Chains with Maximum Entropy Models
This work addresses the challenge of exploratory analysis for intelligence and security domains, where uncovering surprising coalitions is critical, though it appears incremental in combining existing methods with user interaction.
The paper tackles the problem of discovering coordinated relationship chains in massive text datasets, such as those used in intelligence analysis, by introducing new maximum entropy models embedded in a visual analytic system called MERCER, which directs users toward promising lines of inquiry and demonstrates improved validity over purely algorithmic approaches.
Modern visual analytic tools promote human-in-the-loop analysis but are limited in their ability to direct the user toward interesting and promising directions of study. This problem is especially acute when the analysis task is exploratory in nature, e.g., the discovery of potentially coordinated relationships in massive text datasets. Such tasks are very common in domains like intelligence analysis and security forensics where the goal is to uncover surprising coalitions bridging multiple types of relations. We introduce new maximum entropy models to discover surprising chains of relationships leveraging count data about entity occurrences in documents. These models are embedded in a visual analytic system called MERCER that treats relationship bundles as first class objects and directs the user toward promising lines of inquiry. We demonstrate how user input can judiciously direct analysis toward valid conclusions whereas a purely algorithmic approach could be led astray. Experimental results on both synthetic and real datasets from the intelligence community are presented.