UPSI SENTINEL 60 Second Briefing Paper

Page 1

Universities’ Police Science Institute

upsi.org.uk

Sefydliad y Prifysgolion ar Wyddorau’r Heddlu

Sentinel: Localised Situational Awareness via Social Media 60 SECOND BRIEFING

WHAT’S THE KEY IDEA? The Sentinel platform provides a multi-level interface into information extracted from the social Web. The purpose of this platform is to evaluate to what degree web data can be converted into actionable intelligence relating to public-interest events and topics in terms of reliability, usability and timeliness. We focus upon five key questions that can allow human analysts to draw conclusions as to:

What is happening? When is it taking place? Where is it occurring? Who are the sides involved?

Users of Sentinel are able to direct data collection towards specific key words and geographical locations creating “channels” of interest by which intelligence can be derived.

DATA DRIVEN INFORMATION, KNOWLEDGE DRIVEN IDENTIFICATION The data driven text mining tool FlexiTerm[1] has been incorporated into the interface, allowing for a near real time summary of prevailing terms currently found within a channel, with the output being presented spatially and temporally. Running parallel to topic identification is the indexing of data against an expertly curated ontology of criminal and extremist topics. This provides users with the ability to delve deep into their data channels to identify and track sensitive narratives. References:

Why is this happening and why does it require response?

DEALING WITH BIG DATA We take advantage of the pervasiveness of Cloud Computing to create a dynamic and scalable approach to data processing that provides the ability to extract near real time meaning from large volumes of data. This takes the form of a data processing pipeline in which fragments of social media text are filtered, transformed and enriched by a pool of processing and analytic tools.

[1] Spasić, I., Greenwood, M., Preece, A., Francis, N. and Elwyn, G. (2013). FlexiTerm: A flexible term recognition method. Journal of Biomedical Semantics 4:27


Fig 1

Fig 2

LOCALISED SITUATIONAL AWARENESS OF SOCIAL MEDIA Early investigations into situational awareness through social media has lead to the development of a suite of web applications:

Created a multi-level interface into the information we extract. Topic identification is achieved through the use of Flexi-Term Provides both temporal and geographical reference planes Answers the questions “What? When?” and “What? Where?”

CASE STUDY: WOOLWICH INCIDENT 22nd May 2013, killing of Lee Rigby in Woolwich Aggressive reaction from English Defence League Widespread attention from Social Media (464,196 Tweets) FlexiTerm Output Rela

50000

to Woolwich Timeline Response to @BoyaDee

60000

woolwich

rigby

edl

eline of Woolwich events

200

islamist terrorist a ack

180

Men

ns

Re Tweets

160 40000 30000

140 120

police contain edl

protest tea biscuits

drummer lee rigby

20000

second woolwich killer

man stabbed woolwich

edl march newcastle

10000

100 80 60 40 20

0

FUTURE WORK: ENHANCING WHERE, ASKING WHO Named Entity Recognition will identify “Who?” and “Where?” Usability study of interfaces with end users Investigation into the demographics of data sources

0

PARTNERSHIPS:

For further information go to: www.upsi.org.uk e: upsi@cardiff.ac.uk


Turn static files into dynamic content formats.

Create a flipbook
Issuu converts static files into: digital portfolios, online yearbooks, online catalogs, digital photo albums and more. Sign up and create your flipbook.