To detect and monitor terrorist activity, Law Enforcement Agencies (LEAs) increasingly rely on social media intelligence (SOCMINT), a new field covering a wide range of applications, techniques and capabilities for analysing social media data. Red-Alert has created and evaluated an advanced SOCMINT platform for LEAs covering the many social media channels used by terrorist groups.
Researchers
Research background
The Red-Alert consortium was formed in response to a call for proposals within the Horizon 2020 Secure Societies work programme.
The specific challenge identified was to provide Law Enforcement Agencies (LEAs) with the means of combatting organised crime and terrorist organisations who are themselves using advanced technologies in their activities.
Red-Alert is led by SIMAVI, a Romanian company specialising in the execution of complex and sustainable IT projects in the fields of eAgriculture and Cybersecurity. Other partners include:
- LEAs from the UK, Romania, Israel, Spain and Moldova,
- Universities and research institutes from Israel, Hungary and the UK
- Technology-providing companies from the UK, Spain, Israel and Hungary, and a law association from Malta.
Research aims
To outperform state-of-the-art SOCMINT solutions in terms of performance (number of languages supported, number of social media channels mined, and accuracy), usability (visualization, real-time operation, collaboration, development support) and privacy protection.
How has the research been carried out?
The Red-Alert platform integrates advanced technologies such as Natural Language Processing (NLP), Semantic Media Analysis Social Network Analysis (SNA), Artificial Intelligence (AI) and Complex Event Processing (CEP).
BCU is responsible for the Semantic Media Analysis (SMA) tool that interprets image, audio and video files and identifies and tags events and objects of interest. The SMA tool is trained using media files provided by LEAs that we have annotated based on LEA requirements.
The various prototype tools and technologies have been integrated to create a reference platform. Instances of the platform are being deployed on LEA premises and will used for a series of Pilot trials.
Research outcomes
The RED-Alert project has now been completed successfully. The LEA partners have evaluated the platform and confirm that it offers a significant advance over tools they use currently.
The main impacts resulting from using the RED-Alert solution are:
- Improved investigation capabilities
- Crimes solved more rapidly, to reduce societal distress, investigative costs and the impact on victims and their relatives
- Prevention of terrorist endeavours
- Better identification and understanding of criminal activities
- LEA officers provided with better tools to help them on their (specialized) daily work.
Funding information
Funder: European Commission Horizon 2020 (H2020) Programme under Research & Innovation Action H2020-SEC-12-FCT-2016 (Technologies for prevention, investigation, and mitigation in the context of fight against crime and terrorism).
Funding: Total project cost: €5,064,437.5, Grant to BCU: € 243,250
Additional info
Recording of Final RED-Alert Conference: http://redalertproject.eu/final-red-alert-conference