犯罪网络分析和透视：数据挖掘.doc

Criminal Network Analysis and Visualization: A Data Mining Perspective (Forthcoming article accepted for publication in Communications of the ACM) By Jennifer Xu and Hsinchun Chen Criminal Network Analysis After the tragic events of September 11, 2001, academics have been called on for possible contributions in uncovering terrorist networks to enhance public safety and national security. Both the public and the Pentagon have realized that knowledge of the structure of terrorist networks and how those networks operate is one of the key factors in winning the so-called “netwar”. In this new war against terrorists probably the most critical weapons that our intelligence and law enforcement agencies should be armed with are reliable data and sophisticated techniques that help discover useful knowledge from the data. Study of terrorist networks falls into the larger category of criminal network analysis, which is often applied to investigations of organized crimes (e.g., terrorism, narcotics trafficking, fraud, gang-related crimes, armed robbery, etc.). Unlike other types of crimes such as homicide and sex offenses that often are committed by single or a few offenders, organized crimes are carried out by multiple, collaborating offenders. These offenders may form groups and teams and play different roles. In a narcotics network, for instance, different groups may be responsible for handling the drug supply, distribution, sales, smuggling, and money laundering. In each group, there may be a leader who issues commands and provides steering mechanisms to the group, as well as gatekeepers who ensure that information and drugs flow effectively to and from other groups. Criminal network analysis therefore requires the ability to integrate information from multiple crime incidents or even multiple sources and discover regular patterns about the structure, organization, operation, and information flow in criminal networks. To untangle and disrupt criminal networks, both relia