UK team wins global hackathon award for innovative solution to tackle child abuse

AbuSearch used a combination of text analytics and natural language processing as part of SAS’ annual hackathon

A UK-based team has won the ‘Data for Good’ special award in a global hackathon run by data and AI leader SAS. It follows its work using text analytics, natural language processing (NLP) and other tools to tackle online child sexual abuse.

AbuSearch, formed of members from SAS Partner Katalyze Data and the Child Rescue Coalition, aimed to create a solution which could identify users who share or produce harmful content relating to children online, as well as those grooming potential victims.

To do so, they analysed chat and forums data from Project NEMESIS - which automates the handling of evidence for live streaming abuse cases - applying natural language processing, data profiling, visualisation, and network analytics techniques.

The resultant solution cuts through masses of data to create and triage alerts to identify users who share and produce harmful content on children, and find, groom and contact their victims, in addition to showing the network of users.

Analysts are also able to profile text, study term maps, use topic modelling, extract locations from messages and pinpoint the first sharers of harmful content hyperlinks.

It uses various components of the SAS Viya platform to deploy and deliver these insights in an actionable and timely manner, with a summary dashboard available to view in SAS Visual Analytics.

Katalyze Data is an advanced analytics service provider with over 35 years of experience in unlocking the power of data-driven decisions.

Sara Di Donna, Sales Director at Katalyze Data, commented:

“After a chance meeting at SAS Innovate on Tour, we recognised the opportunity for Katalyze Data to work with the Child Rescue Coalition to help identify child abusers online.

“Up to 85 per cent of online offenders are hands-on abusers of children, with as many as one in five girls and one in 20 boys experiencing some form of sexual abuse before the age of 18. This project has the potential to enact real change, with NLP uniquely positioned to generate tangible insights.”

The Child Rescue Coalition is a Florida-based not-for-profit organisation which operates worldwide to provide free software to law enforcement to tackle the threat of child sexual abuse and exploitation.

Phil Attwood, Director of Impact at the Child Rescue Coalition, said:

“I was really proud to work with the team to advance our abilities to identify threat, risk, and harm from different data sources, in close to real-time. Analysing data from a range of online platforms, we were also able to increase our understanding of high harm threats and links between offenders.

“Artificial intelligence technology will have a huge impact in the future in helping us be more efficient and use finite resources for law enforcement more effectively. We hope it will help progress our mission to help officers identify, arrest and prosecute child predators, in the UK and internationally.”

Ashley Beck, Senior Law Enforcement Industry Consultant at SAS UK & Ireland, added:

“AbuSearch’s entry stood out to our team of judges, showcasing the very best of how technology can be used to tackle important issues. NLP makes it possible for computers to interpret text and speech, measure sentiment and determine which parts are important, all of which has been transformational when working with vast amounts of data.”

This year’s SAS Hackathon saw 1,731 registrants from more than 70 countries take part in a month-long hack, which was sponsored by long-time SAS Partners Microsoft and Intel.

To find out more about AbuSearch’s entry, visit https://communities.sas.com/t5/SAS-Hacker-s-Hub/AbuSearch/ta-p/941672