Cyber Crime and Cyber Terrorism

1. 
Crawling and monitoring social media sources by tracking public comments and 
scraping criminal profiles and posts
2. 
LEAs direct communication and interaction with public from their own social 
media accounts
3. 
LEA coordinated crowd-sourced information
After the collection of these data LEAs must extract, clean, filter and aggregate the 
unstructured data into machine readable formats. The types of data retrieved can 
include:
• Unstructured text from tweets and other postings
• Video and images
• Geographic information

---

215
 
LEA usage scenarios for social media
• Social network information
• Personal details including age, location, family, likes, dislikes, etc.
Having gathered all these data, it needs to be processed and analyzed so that it can be 
used as by LEAs in a meaningful way. Examples of such techniques are:
• Facial recognition and matching from picture to images held on file
• Profile matching between social media platforms and police reports
• Natural language processing to make sense of unstructured text
• Sentiment analysis to monitor public opinion
• Geo-tagging and location resolution to track movements and key places
• Social network analysis to map friends, acquaintances and interactions
These disparate analyses can then be filtered, processed and consolidated into ac-
tionable, credible information and further assessed by those with domain expertise. 
The results of these processes may then be applied to a number of scenarios such as 
organized crime, lone-wolf, human trafficking, hostage situations and crisis and ter-
rorist events as described earlier in this chapter. This, however, is not the end of the 
loop. Throughout the process as more intelligence is harvested it is fed back into the 
search to refine and make the tools more accurate and targeted, enabling it to account 
for new information to strengthen the potential outcomes for LEAs and increase the 
validity of their intelligence.
Social media
monitoring
and
intelligence
gathering
Direct
communication
from LEAs
Social media
Data
Personal
information
Profile
matching
Facial
recognition
Hostage
situations
Lone wolf
Trafficking
of human
beings
Crisis and
terrorism
Organized
crime
Natural
language
processing
Sentiment
analysis
Geotagging
and mapping
Social
network
analysis
Intelligence filter
Video/images
Text
Geographic
Social
network
Feedback loop
Cleaning
Filtering
Public
commentaries
and crowd
sourcing
Da
ta e
xtraction
Da
ta
a
gg
reg
ation
Open source
intelligence
Value added knowledge
processing
LEA
intelligence