Understanding the Dynamics of Unclaimed Terrorism Events in Pakistan: A Machine Learning Approach
General Material Designation
[Thesis]
First Statement of Responsibility
Christie, Evan
Subsequent Statement of Responsibility
Asif Nawaz, Muhammad
.PUBLICATION, DISTRIBUTION, ETC
Name of Publisher, Distributor, etc.
The University of Maine
Date of Publication, Distribution, etc.
2019
GENERAL NOTES
Text of Note
55 p.
DISSERTATION (THESIS) NOTE
Dissertation or thesis details and type of degree
M.A.
Body granting the degree
The University of Maine
Text preceding or following the note
2019
SUMMARY OR ABSTRACT
Text of Note
Terrorists thrive on media coverage because it multiplies the effect of an attack (Nacos, 2007). However, according to the Global Terrorism Database (GTD), only ten percent of terrorist attacks have been attributed globally from 1970 to 2017 (START, 2017). If the media coverage is a prerequisite for a terrorist group's survival, the lack of attributed attacks in the world is puzzling. This thesis examines the phenomenon of unattributed terrorist attacks using Pakistan as a case study. Pakistan is used as a case study because the percentage of claimed terrorist attacks in Pakistan closely resembles the global average of the lack of attribution of terrorist attacks - only fifteen percent of attacks are attributed in Pakistan. By using different organizational attributes - like attack, target, weapon preferences, spatial attack data, and lethality of attacks, this study attempts to match unattributed terror attacks to known groups.