Communications of the ACM
To Catch a Cyber-Thief
Researchers say their new method for analyzing computer data that automatically identifies criminal topics in a textual conversation could slash data-crunching time from months to minutes.
Credit: NAHB News
Concordia University researchers have developed a method for analyzing computer data that automatically identifies criminal topics discussed in a textual conversation. The method also shows which participants are most active with respect to the identified criminal topics, and provides a visualization of the social networks among the participants.
The researchers say their method could slash data-crunching time from months to minutes. "Our new technique allows an investigator to cluster documents by producing overlapping groups, each corresponding to a specific subject defined by the investigator," says Gaby Dagher, a researcher at the Concordia Institute for Information Systems Engineering. "Experiments using real-life criminal data already suggest that our approach is much more effective than the traditional methods."
The researchers also have developed a new search engine to help investigators identify the relevant documents from a large volume of text. "Our search engine captures the suspects’ vocabulary, and then uses it to improve the accuracy of the search results," Dagher notes. "This search engine allows investigators to pick up on [the nuances of criminal vocabulary] and quickly identify the incriminating documents."
From Concordia University
View Full Article
Abstracts Copyright © 2013 Information Inc., Bethesda, Maryland, USA
No entries found