A Visual Analytics Approach To Explore Potential Anomalous Behavior in Corporate Communication
Bo Cun Sun, Ce Pang · 2021
In this paper, we present a visual analytics approach to analyze temporal patterns of human communication from a vast corporate communication dataset. Our approach mainly relies on visualization and mapping techniques to discover the patterns, which then support feature model development for a machine learning method. In contrast to previous work, our technique targets communication data presenting only temporal and interaction information, and focuses on the pattern searches of anomaly behaviors. The new visual analytics platform can be effectively used to analyze the differences between normal and suspicious procurement behaviors in corporation using email, phone call, and personal meeting records. By using the platform, we successfully found other potentially illegal activity based on suggested suspicious behaviors.