The not yet exploited goldmine of osint: Opportunities, open challenges and future trends

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