April 21, 2018
“A new computer algorithm may help identify sexual predators who target children in chatrooms. The algorithm dubbed CATT can identify language differences and self-disclosure in conversations to provide a risk assessment of potential predators, researchers report.” Neurosciencenews.com
Purdue Polytechnic Institute faculty developed an algorithm tool that “will help law enforcement filter out and focus on sex offenders most likely to set up face-to-face meetings with child victims.”
Principal investigator Kathryn Seigfried-Spellar, assistant professor of computer and information technology, presented the Chat Analysis Tool (CATT) at the International Association of Law Enforcement Intelligence Analysts Conference in Anaheim California.
Sexual predators solicit minors to engage in sexual fantasy chats or even to set up face-to-face meetings with them.
Law enforcement officers are inundated with these cases. Characteristics of sexual predators groom victims for a face-to-face meeting for weeks or even months until a meeting is achieved.
With this tool that identifies language differences in the chats officers can perform risk assessments and probabilities that a person is a sexual predator and is attempting to set up a meeting.
The project started as a result of a partnership with Ventura County Sheriff’s Department in California.
“Seigfried-Spellar said that research discovered tactics like self-disclosure is used early in a predator’s talks with a potential victim.”
Two co-principal investigators were associate professor Julia Taylor Rayz who specialized in machine learning and natural language processing and Marcus Rodgers, who heads the computer and information technology department has an extensive background in digital forensics development.
Initial research was done by Seigfried-Spellar and former Purdue professor Ming Ming Chiu. They studied 4,300 messages in 107 chats involving arrested sex offenders and identified word usage and self-disclosure by fantasy.
The trends determined through this research formed the basis for CATT. The research, “Detecting Contact vs. Fantasy Online Sexual Offenders in Chats with Minors: Statistical Discourse Analysis of Self-Disclosure and Emotion Words”, has been accepted and will be published in the journal “Child Abuse and Neglect.”