The article assigned as a reading for this lesson (Koschade, Stuart. 2006. A Social Network Analysis of Jemaah Islamiyah: The Applications to Counterterrorism and Intelligence . Studies in Conflict and Terrorism. Vol. 29 Issue 6, pp. 559 - 575) presents an analysis of the Jemaah Islamiyah cell that was responsible for the Bali bombings in 2002. The data from this paper (tables 1 and 2) are available to you as the following CSV files:

library(igraph)
## 
## Attaching package: 'igraph'
## The following objects are masked from 'package:stats':
## 
##     decompose, spectrum
## The following object is masked from 'package:base':
## 
##     union
  1. Read in the data.
Table1 <- read.csv('846 Lesson 5 2006 Koschade Table 1.csv', header=TRUE, row.name=1)
Table2 <- read.csv('846 Lesson 5 2006 Koschade Table 2.csv', header=TRUE, row.name=1)
head(Table1)
##          Muklas Amrozi Imron Samudra Dulmatin Idris Mubarok Azahari Ghoni
## Muklas        0      1     1       1        1     1       0       1     1
## Amrozi        1      0     0       1        0     1       1       0     0
## Imron         1      0     0       1        1     1       0       1     1
## Samudra       1      1     1       0        1     1       1       1     1
## Dulmatin      1      0     1       1        0     1       0       1     1
## Idris         1      1     1       1        1     0       1       1     1
##          Arnasan Rauf Octavia Hidayat Junaedi Patek Feri Sarijo
## Muklas         0    0       0       0       0     1    0      1
## Amrozi         0    0       0       0       0     0    0      0
## Imron          0    0       0       0       0     1    1      1
## Samudra        1    1       1       1       1     1    0      1
## Dulmatin       0    0       0       0       0     1    1      1
## Idris          0    0       0       0       0     1    0      1
dim(Table1)
## [1] 17 17
head(Table2)
##          Muklas Amrozi Imron Samudra Dulmatin Idris Mubarok Azahari Ghoni
## Muklas        0      2     2       1        1     5       0       1     1
## Amrozi        2      0     0       2        0     4       5       0     0
## Imron         2      0     0       3        5     3       0       5     5
## Samudra       1      2     3       0        2     5       2       2     2
## Dulmatin      1      0     5       2        0     2       0       5     5
## Idris         5      4     3       5        2     0       2       2     2
##          Arnasan Rauf Octavia Hidayat Junaedi Patek Feri Sarijo
## Muklas         0    0       0       0       0     1    0      1
## Amrozi         0    0       0       0       0     0    0      0
## Imron          0    0       0       0       0     5    1      5
## Samudra        2    2       2       2       2     2    0      2
## Dulmatin       0    0       0       0       0     5    1      5
## Idris          0    0       0       0       0     2    0      2
dim(Table2)
## [1] 17 17
relations <- as.matrix(read.csv('846 Lesson 5 2006 Koschade Table 2.csv', header =T, row.names = 1))
g <- graph.adjacency(relations, mode = "undirected", weighted = TRUE)
summary(g)
## IGRAPH 9caf2ef UNW- 17 63 -- 
## + attr: name (v/c), weight (e/n)
  1. Plot the network similar to the one shown in Figure 1 of the article.
plot(g, layout = layout_with_kk, vertex.label.cex = 0.75, edge.width=E(g)$weight)

  1. Use the following ten topographical measures for characterizing and analyzing the network:
  1. Size
  2. Distance
  3. Diameter
#a
size_g <- length(V(g))

#b
average_distance_g <- mean_distance(g)

#c
diameter_g <- diameter(g)

basic_topography_g <- matrix(c(size_g, average_distance_g, diameter_g), nrow=1, ncol=3)
colnames(basic_topography_g) <- c('size', 'average distance', 'diameter')

as.table(basic_topography_g)
##        size average distance  diameter
## A 17.000000         1.588235  6.000000
  1. Centralization
  2. Standard Deviation
#d and e
degree_centralization_g <- centralization.degree(g)$centralization
degree_sd_g <-sd(centralization.degree(g)$res)

closeness_centralization_g <- centralization.closeness(g)$centralization
closeness_sd_g <-sd(centralization.closeness(g)$res)

betweenness_centralization_g <- centralization.betweenness(g)$centralization
betweenness_sd_g <- sd(centralization.betweenness(g)$res) 

centralization_g <- matrix(c(degree_centralization_g, degree_sd_g, closeness_centralization_g, closeness_sd_g, betweenness_centralization_g, betweenness_sd_g), nrow=1, ncol=6)
colnames(centralization_g) <- c('degree cent', 'degree cent. SD', 'closeness cent.', 'closeness cent. SD', 'betweenness cent.', 'betweenness cent. SD')

as.table(centralization_g)
##   degree cent degree cent. SD closeness cent. closeness cent. SD
## A   0.4742647       3.0012252       0.6503460          0.1079152
##   betweenness cent. betweenness cent. SD
## A         0.4999132           14.6311750
  1. Density
  2. Average degree
  3. Cohesion
  4. Compactness
  5. Global clustering coefficient
#f
density_g <- edge_density(g)
#g
average_degree_g <- mean(degree(g))
#h
cohesion_g <- cohesion(g)
#i
compactness_g <- mean(closeness(g))
#j
global_clustering_coefficient_g <- transitivity(g,type="global")

interconnectedness_g <- matrix(c(density_g, average_degree_g, cohesion_g, compactness_g, global_clustering_coefficient_g), nrow=1, ncol=5)
colnames(interconnectedness_g) <- c('density', 'average degree', 'cohesion', 'compactness', 'global clustering coefficient')

as.table(interconnectedness_g)
##      density average degree   cohesion compactness
## A 0.46323529     7.41176471 1.00000000  0.02045028
##   global clustering coefficient
## A                    0.78781513

NOTE: The article uses a number of centrality measures (as opposed to centralization measures). Centrality measures are more focused on individual actors within the network whereas centralization focuses more on the overall topography of the network. These two terms are easily confused. For this assignment we will only work with centralization measures.