Preece, Alun David ![]() ![]() ![]() |
Preview |
PDF
- Submitted Pre-Print Version
Download (5MB) | Preview |
Abstract
Rapid processing and exploitation of open source information | including social media sources | in order to shorten decision-making cycles, has emerged as an important issue in intelligence analysis in recent years. Through a series of case studies and natural experiments, focussed primarily upon policing and counter-terrorism scenarios, we have developed an approach to information foraging and framing to inform decision making, drawing upon open source intelligence | in particular Twitter, due to its real-time focus and frequent use as a carrier for links to other media. Our work uses a combination of natural language (NL) and controlled natural language (CNL) processing to support information collection from human sensors, linking and schematising of collected information, and the framing of situational pictures. We illustrate the approach through a series of vignettes, highlighting (1) how relatively lightweight and reusable knowledge models (schemas) can rapidly be developed to add context to collected social media data, (2) how information from open sources can be combined with reports from trusted observers, for corroboration or to identify con icting information; and (3) how the approach supports users operating at or near the tactical edge, to rapidly task information collection and inform decision-making. The approach is supported by bespoke software tools for social media analytics and knowledge management.
Item Type: | Conference or Workshop Item (Paper) |
---|---|
Date Type: | Completion |
Status: | Unpublished |
Schools: | Computer Science & Informatics Crime and Security Research Institute (CSURI) Social Sciences (Includes Criminology and Education) |
Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
Date of Acceptance: | 16 December 2015 |
Last Modified: | 01 Nov 2022 09:50 |
URI: | https://orca.cardiff.ac.uk/id/eprint/89374 |
Citation Data
Cited 1 time in Scopus. View in Scopus. Powered By Scopus® Data
Actions (repository staff only)
![]() |
Edit Item |