A Visual Analytics Approach to Explore Potential Anomalous Behavior in Corporate Communication

Bo Sun, Ce Pang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

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.

Original languageEnglish (US)
Title of host publicationICCDA 2021 - Proceedings of the 2021 5th International Conference on Compute and Data Analysis
PublisherAssociation for Computing Machinery
Pages119-128
Number of pages10
ISBN (Electronic)9781450389112
DOIs
StatePublished - Feb 2 2021
Externally publishedYes
Event5th International Conference on Compute and Data Analysis, ICCDA 2021 - Sanya, China
Duration: Feb 2 2021Feb 4 2021

Publication series

NameACM International Conference Proceeding Series

Conference

Conference5th International Conference on Compute and Data Analysis, ICCDA 2021
Country/TerritoryChina
CitySanya
Period2/2/212/4/21

All Science Journal Classification (ASJC) codes

  • Software
  • Human-Computer Interaction
  • Computer Vision and Pattern Recognition
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'A Visual Analytics Approach to Explore Potential Anomalous Behavior in Corporate Communication'. Together they form a unique fingerprint.

Cite this