ReDites: Real Time, Detection, Tracking, Monitoring and Interpretation of Events in Social Media

Lead Research Organisation: University of Edinburgh
Department Name: Sch of Informatics


The project will develop a demonstrator capable of bringing together isolated strands of research on event detection, monitoring, interpretation, tracking and visualisation into a single system capable of situation awareness. The outcome will be an end-to-end demonstration from detecting an event/incident, through to being able to see what is going on, characterising/summarising the event, tracking, and monitoring.

Planned Impact

The project will enable the Intelligence Services, MOD, police and Emergency Services to improve their situational awareness by the identification, interpretation and monitoring of events while they are happening. It utilises people's desire to broadcast observations and opinions on the events around them, from simply describing and discussing the evolution of situations, to informing others of their whereabouts and safety and organising themselves. The Arab Spring uprisings are a well documented example of how social media was of fundamental importance in the organisation of the protests and dispersal information. However, while such communication has proven benefits, there is also a risk of anti-social and criminal activities (e.g. to incite violence during the UK riots in August 2011).

Recent governmental reports continue to emphasise the importance and potential benefit of monitoring social media. In the USA the Department of Homeland Security reports on Media Monitoring and Terrorism state "Social Media outlets provide instant feedback and alert capabilities to rapidly changing or newly occurring situations" [1], and that there has been a "...marked a shift in the use of social media in disasters. More than ever before, government agencies turned to mobile and online technologies." [2]. In the UK, a report considering the financial constraints on policing stated that "...[police] need to use existing resources more smartly and free them up to act on intelligence - not be bogged down by sifting through information. Most importantly they need to use technology wisely to extract actionable intelligence from mass social media data. The police will only be able to bring the current profusion of data under control through the use of analytics, enabling them to action intelligence and use it to help prevent a range of crimes...." [3].

The technology proposed in this project will combine efficient analytical algorithms, implemented on robust distributed technologies, to enable harvesting of real-time information directly from massive, incomplete, contradictory, noisy and distributed social media data. We will build on technology and know-how developed within the various partners' Daisy projects, integrating and improving the technologies to provide a comprehensive and coherent approach to social media event mining. Moreover, we will create demonstrators of capabilities that are made possible by the research to showcase the project outcomes to potential beneficiaries:

(i) The project will developed state of the art in social media mining technologies that aim to be commercialised and applied in subsequent projects. Currently social media monitoring is focusing on trend rather than event detection, the project will enable tools to move beyond these limitations.

(ii) The project will provide a feasibility study on the use of social media event monitoring for intelligence. The technology developed in the project will enable an insight into security related events as they arise, both national and international. We plan to test the developed technology on data collected during emergencies and crises that develop during 2013, demonstrating how future events could be monitored.

(iii) Both individual citizens and society at large will benefit from the results of the project through improved security nationally and internationally. More directly, the ability to gain intelligence through the use and analysis of social media may be reused, e.g. for education and to encourage civic engagement.

[1] DHS Analyst's Desktop Binder -- DHS National Operations Center Media Monitoring Capability, 2011

[2] Fraustino, J.D., B. Liu and Y. Jin. "Social Media Use during Disasters: A Review

of the Knowledge Base and Gaps," Final Report to DHS, 2012


Social Media in Public Security: Finding a Way Forward, April 2013


10 25 50
publication icon
Zhao W (2015) Incorporating Social Role Theory into Topic Models for Social Media Content Analysis in IEEE Transactions on Knowledge and Data Engineering

Description We developed a system that would find events in twitter, summarise, predict emotional labels (when necessary) and would geolocate them. This can be used to for crisis management.
Exploitation Route Our approach can be used to help manage disasters such as earthquakes, riots or shootings.
Sectors Aerospace, Defence and Marine,Digital/Communication/Information Technologies (including Software),Government, Democracy and Justice

Description We developer a demonstrator that we show-cased to Government agencies.
First Year Of Impact 2014
Sector Aerospace, Defence and Marine,Government, Democracy and Justice
Impact Types Policy & public services