الفهرس 
A dynamic network analysis for Syrian crisis
AbstractOnly 14 pages are availabe for public view
 |  | from | 131 |  |  |
| | | from | 131 | | |
Abstract
This study examines the extent to which dynamic network Analysis (DNA) and natural language processing (NLP) are helpful research tools in identifying the key actors in a complex international crisis. The study uses these tools to identify the key actors in the Syrian crisis. The importance of the study lies in two main points; firstly, it proposes an algorithm that mixes NLP, network extraction from textual unstructured data, and DNA in order to understand and monitor changes occurring in an international crisis. Furthermore, it applies the proposed algorithm on the Syrian crisis to identify the key actors.Although there are several resolutions of the UN Security Council that stipulated the need to stop fighting and start a political process, the nature of the Syrian crisis is characterized by the intransigence and refusal to make serious concessions, as well as, the multiplicity of regional, international and local key players in Syrian affairs. Besides that, there are some other factors such as the fragmentation of the opposition forces and armed groups and the divergence of their objectives. In addition to prolonging the Syrian crisis with social divisions, there were tragedies and atrocities between components and segments of Syrian society because of violence and counter-violence.Therefore, the Syrian crisis is considered a pivotalcase study that can be analyzed using a dynamic network analysis technique to study the situation, which consists of different types of nodes and varies from one point time to another. Studying the Syrian crisis as a dynamic social network is helpful indetermining the key actors of the crisis and how they are changing over time. The analysis was divided into four levels; state level, politicians’ level, formal organizations, and informal organizations.This analysis was performed using the temporal eigenvector centrality measure to detect the leaders of strong cliques at each level.The results reveal changes in actors’ powerful positions in 2012 and 2016, which match the changes that occurred in the political arena