الفهرس | Only 14 pages are availabe for public view |
Abstract The current study presents an extension of the category of social network analysis studies using control charts. The analysis is performed on two main aspects related to social network monitoring. First,a change detection performance comparison among some network centrality measures (betweenness, closeness, and degree) via control charts is conducted on weighted and unweighted directed networks. Two descriptive measures were identified; which are the average, and standard deviation for each metric. Simulation results show that, in directed networks, the degree centrality measure in most cases is recommended to be used for both weighted and unweighted networks except for some specific situations; in which the betweenness and/ or closeness measures are highly recommended. Also, it can generally be concluded that taking the average of each centrality measure performs better than taking the standard deviation in detecting anomalies |