B. OSINT ANALYSIS
The continuous iterations through the different OSINT tech-
niques should be analyzed and understood to generate valu-
able information. There is an increasing amount of analysis
techniques in the literature to do this task [46], highlighting
below those appealing procedures which are applicable in our
scenario:
•
Lexical analysis
: Raw data should be examined to ex-
tract entities and relations from text. It is essential to
apply translation processes to the language used in the
OSINT investigation [47] and filter noise which does not
add value from sentences that do not add value.
•
Semantic analysis
: Having a bag of words is not useful
if the meaning is not extracted [48]. With this purpose
of understanding data, natural language processing al-
gorithms are being used nowadays [49]. In addition,
sentiment analysis techniques permit the contextual-
ization of subjective posts or opinions to classify the
emotional status of the author (e.g, positive, negative or
neutral). Finally, truth discovery procedures address the
challenging task of resolving conflicts in multi-source
data which stands opposing positions on the same sub-
ject [50].
•
Geospatial analysis
: Recollected data from social net-
works, events, sensors or IP addresses are worthwhile
to be analyzed from a location-based perspective. In
this sense, the usage of maps or graphs facilitates the
representation and comprehension of data [51], as well
VOLUME 4, 2016
5
This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/.
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2020.2965257, IEEE Access
J. Pastor-Galindo et al.: The not yet exploited goldmine of OSINT: Opportunities, open challenges and future trends
Location
Social
networks
User name
Real name
Search
engines
Domain
name
IP address
Email
address
Telephone
Education
Professional
career
Files,
Images
Subdomains
Registration
info
City,
Country
Age
GPS
coordinates
Website
Company
Operating
system
Hostnames
CV
Political, sexual or
religious preferences
Tendency to crime
Economic situation
Cached life
Places visited
Activity on
the web
Crime attribution
De-anonymization
Relatives
Location
IP address
Email
address
User name
Real name
Domain
name
Network
topology
DNS
records
Organizational information
Personal information
Network information
Output
info
Knowledge
elicitation
Potential
findings
Data
transfer
OSINT techniques
A N A L Y S I S
Lexical
analysis
Semantic
analysis
Geospatial
analysis
Social media
analysis
C O L L E C T I O N
Tracking
patterns
Classification
Correlation
Outlier
detection Clustering Regression
K N O W L E D G E E X T R A C T I O N
Media
Government
data
Internet
Commercial
data
Network
infrastructure
Do'stlaringiz bilan baham: |