Digital Police Officer: Linguistic Analysis to Identify Cybercriminals

The concept of ‘trust’ is paramount online: users encounter one another in an unmediated space in which impersonation is easy, and phishing and harassment are common . Concerns about the impact of untrustworthy and criminal behaviours on the Web have grown substantially in recent years, with cybercrime costing UK businesses an estimated average of £3m a year.

It is notoriously difficult to establish trust online: for example, consider a user who has been expelled from an online forum, but returns using another nickname. How can we know that the person we are interacting with is not this individual? How could anyone seeking to police the Internet determine if it is the banned individual?

This project investigates linguistic analysis as a possible solution, through a demo to identify an online user by the way in which they communicate. The approach is to analyse the characteristics of forum users (i.e. based on their vocabulary and grammar) to build a linguistic fingerprint using Natural Language Processing technologies.

The effectiveness of the approach will be assessed in the context of law enforcement. We consider carding forums, venues for buying and selling stolen credit card data. When one carding forum closes, another rises: criminals with a trusted reputation on a defunct site ‘port’ their reputations to another without necessarily keeping the same username or other identifying features. This project will determine to what extent current linguistic analysis technologies can track such users, with potential applications in interpersonal trust online as well as law enforcement.

This project is funded by the Web Science Institute.

DPO organisations and links

The following organisations, all part of the University of Southampton, are collaborating in the Digital Police Officer project:

Related Twitter accounts:

The project is funded by the Web Science Institute.

DPO resources

This page provides resources related to the Digital Police Officer project:

  • DPO poster, presented at: ‘Web Science Institute One Year On: Privacy and Trust in the Era of Big Data Analytics’
  • DPO abstract accepted at EUROCRIM2015, on ‘The pleasures and pains of transdisciplinary research for Criminology: Insights from the Digital Police Officer Project’

Web Science Institute: Privacy and Trust in the Era of Big Data Analytics

On 8th June members of the Digital Police Officer (DPO) team made a trip to London to present a poster at Privacy and Trust in the Era of Big Data Analytics, an event organised by the Web Science Institute celebrating their first birthday. The event was hosted on the ninth floor of the Digital Catapult Centre, which provided stunning views of the skyline of the city of London. Despite the amazing views next to our poster (which you can view on our DPO Resources page), we still got lots of interest in our ongoing research. With interdisciplinary topics such as privacy, trust and security on the Web being the main focus of the day, DPO’s interdisciplinary focus also drew a lot of attention from visitors. We talked to people from academia, law enforcement and industry.

The event opened with a lively poster session in which we held our first wave of conversations. After that the afternoon’s panel sessions started with a fascinating discussion on digital privacy and security between Sir David Omand and Mr Philip Sheldrake, chaired by Dame Wendy Hall. As former head of GCHQ, Omand’s views clashed with technologist Sheldrake. Nonetheless, both Omand and Sheldrake presented compelling arguments for and against encryption. This was followed by equally lively panels on Private and Personal Data in the Age of the Web of Data (chaired by Sir Nigel Shadbolt with Gavin Starks, Liz Brandt and John Taysom as speakers), and Algorithms and Accountability (chaired by Professor Susan Halford with Dr Dan McQuillan, Dr Caroline Wilson and Dr Alison Powell as speakers). The final panel, chaired by Professor Les Carr, had three students from the University of Southampton Web Science Centre for Doctoral Training as speakers and focused on their current research on personal data.

Our conversations with interested people about DPO continued during the breaks in between and after the panel sessions. Overall, it was a very enjoyable day and moreover it very useful for the project as well. After the Second Southampton Cybercrime Symposium in March, this was the second event at which we presented a poster. Such events pose a useful avenue for us to show the impact of our research and to start discussions with external parties. We already look forward to the next such event, when we can present the progress we have already made since the 8th June!