Transcript Detecting terrorist activities

Detecting terrorist activities
Presentation on a specialist topic in Data
Mining and Text Analytic
Summary

Definitions

Why use it

Techniques

Conclusion
What It is
Terrorists are people who resort to physical/psychological
means of pressuring people in response to their own
beliefs and opinions
This can be for a number of reasons such as political
gain, social/global awareness
Can be used to set an example.
Would you class strike as a form of terrorists activity?
Medium
Traditional methods- repeat offenders
Social Media
Cults and organisations
Encrypted Messages
Techniques
Keyword/Text extraction
Intrusion Detection
Vector-Space Model
Information Extraction
Automatic Text Summaries
Keyword Extraction

“Terror” Corpus

Multiple Language

statistical techniques

“Aboutness” of a text or genre

Keyword Total/Percentage
Intrusion Detection

Monitor/Analyse actions

Decision making- Hostile

Database of information


Current Systems

Data logs
Algorithm

% normal action vs intrusive action
Idea
Data mining works best when you're searching for a welldefined profile, a reasonable number of attacks per
year and a low cost of false alarms.
Terrorist plots are different. There is no well-defined
profile and attacks are very rare. Taken together, these
facts mean that data-mining systems won't uncover
any terrorist plots until they are very accurate, and that
even very accurate systems will be so flooded with
false alarms that they will be useless.
Conclusion

Privacy Issues

Ambiguity- Text

Very Rare

Pattern Seeking/ Counting Things

Hard to distinguish

Further Development needed