Researchers at the Purdue Polytechnic Institute in the US have developed an algorithm capable of recognizing sexual offenders, especially child predators, who set up face-to-face meetings with children in online chat rooms. If everything goes as planned, this program is intended to help the police by the end of this year.
The algorithm has been named The Chat Analysis Triage Tool (CATT), and it allows officers to work through the volume of solicitations and later using the algorithms to examine the word usage and conversation patterns often used by a potential sexual predator.
While creating this algorithm, researchers at the Purdue Polytechnic Institute analyzed more than 4,300 messages used in 107 online discussions, and it involved previous messages used by sexual predators who were arrested in the past. Studying these messages helped the researchers to identify common redundancies in the words used by these offenders particularly during the time of self-disclosure.
According to the researchers, self-disclosure is a tactic mostly used by these sexual offenders to gain the trust of the victim. In most of the times, these offenders share personal stories, usually negative including parental violence.
"We went through and tried to identify language-based differences and factors like self-disclosure. If we can identify language differences, then the tool can identify these differences in the chats in order to give a risk assessment and a probability that this person is going to attempt a face-to-face contact with the victim. That way, officers can begin to prioritise which cases they want to put resources toward to investigate more quickly," said Kathryn Seigfried-Spellar, an assistant professor at the Purdue Polytechnic Institute.
Seigfried-Spellar also added that usage of this algorithm by law enforcing agencies could potentially stop a sex offense from occurring.
"Meaning that we could potentially stop a sex offence from occurring because if law enforcement is notified of a suspicious chat quickly enough, CATT can analyze and offer the probability of a face-to-face. We could potentially prevent a child from being sexually assaulted," added Seigfried-Spellar.
Initially, this advanced new tool will be handed over to several police units for a test, and later, by the end of this year, it will be widely implemented.
