This link has been bookmarked by 38 people . It was first bookmarked on 20 Nov 2006, by Ole C Brudvik.
-
15 Aug 15
-
18 Aug 13
-
14 Jul 12
-
Figure 16. Clusters of Occupations.
-
Alba and Kadushin's Image of Contacts among Intellectual Elites.
-
Figure 22. The Data of Figure 17 Displayed as a Galois Lattice.
-
-
13 Nov 11
-
28 Apr 11
-
03 Dec 10
-
02 Nov 10
-
12 Jul 10
-
06 Oct 09
-
29 Mar 09
-
09 Oct 08
-
09 Sep 08
ken .Linton Freeman's history of network analysis, relationships in the space-between, from Moreno's hand drawn diagrams (1934) - cliques, clusters, proximity - to simulated spring embedding etc., a hat tip to Koestler (imagery and insightful thinking) and a q
graphics history mapping network science progress social structure thinking visualization
-
03 Sep 08
-
02 Sep 08
-
08 Aug 08
-
18 Jul 08
-
Visualizing Social Networks
Linton C. Freeman -
ABSTRACT: This paper documents the use of pictorial images in social network analysis. It shows that such images are critical both in helping investigators to understand network data and to communicate that understanding to others.
The paper reviews the long history of image use in the field. It begins with illustrations of the earliest hand-drawn images in which points were placed by using ad hoc rules. It examines the development of systematic procedures for locating points. It goes on to discuss how computers have been used to actually produce drawings of networks, both for printing and for display on computer screens. Finally, it illustrates some of the newest procedures for producing web-based pictures that allow viewers to interact with the network data and to explore their structural properties.
-
-
17 Jul 08
-
-
06 Jul 08
peir ricThis paper documents the use of pictorial images in social network analysis. It shows that such images are critical both in helping investigators to understand network data and to communicate that understanding to others.
-
19 Feb 08
-
07 Nov 07
-
01 Apr 07
-
20 Nov 06
-
Visualizing Social Networks
-
This paper documents the use of pictorial images in social network analysis. It shows that such images are critical both in helping investigators to understand network data and to communicate that understanding to others.
-
Two distinct forms of display have been used to construct images of networks, one based on points and lines and the other on matrices.
-
matrix displays the rows and columns both represent social actors and numbers or symbols in the cells show the social connections linking those actors.
-
Duquenne (1993) wrote a program called GLAD that is designed to organize network data into a Galois lattice (Freeman and White, 1993). Like correspondence analysis, a Galois lattice is designed to deal with two mode data. But a Galois lattice embodies a completely different approach and it produces a different arrangement of points. It displays an order structure, one in which the dependencies among the row objects, the dependencies among the column objects and those between the two are simultaneously revealed.
-
That same year Klovdahl reported adapting ORTEP, an early program designed to produce images of molecules, to the production of network images. Four years later he (1982) published an ORTEP-produced picture. It is shown in Figure 20.
Figure 19. Alba and Kadushin's Image of Contacts among Intellectual Elites.
Figure 20. ORTEP Rendition of the Data of Figures 9 and 10.
Figure 21. Images of Social Links in Canberra Australia.
-
All of these properties are displayed in the pattern of proximities
-
es > of Figure 18.
-
Levine (1979) introduced a tool that could be used to locate points in two mode network data. In two mode data the columns and the rows of the data matrix refer to different objects. And Levine's algorithm allows the user simultaneously to assign locations to points of both kinds: those associated with the rows of a data matrix and those associated with the columns. This procedure has many names, but it is now generally known as correspondence analysis.
-
Laumann and Guttman studied the links among 55 occupational categories. They asked individuals to report their own occupations and those of seven of their close associates. Then they built a 55 by 55, occupation by occupation, matrix and tabulated the frequencies in which a respondent's occupation was paired with each of the others.
They then used multidimensional scaling to map the data matrix into a three-dimensional array. Multidimensional scaling is like factor analysis in that is a procedure for data reduction. The investigator begins by specifying the number of dimensions desired in a solution, say 1 or 2 or 3. Then the original data are entered and the multidimensional scaling program finds the best possible arrangement of points -- the one that come closest to capturing patterning in the original data -- in the specified number of dimensions.
The three-dimensional solution obtained by Laumann and Guttman is shown in Figure 16. They used that image to define the 17 occupational clusters shown. In general, each of their clusters contains occupations that have similar prestige levels. High prestige occupations are displayed at the top of the diagram and low prestige ones at the bottom.
Figure 16. Clusters of Occupations.
Figure 17. Links between Corporations and Corporate Directors.
Figure 18. Individual and Corporate Proximities (Levine, 1979).
-
By the 1960s computers were generally available. That provided the opportunity for the use of more elaborate computations. Laumann and Guttman (1966) used a computationally demanding procedure, multidimensional scaling, as a device for locating points from a network analysis. And they were the first to produce an image that was designed to give the appearance of three dimensions.
-
The study included a questionnaire that was administered to the heads of households in two communities. One of the questions was "In case of a death in the family, whom would you notify first?" The answers to that question were examined in detail. Proctor counted the "agreements," the number of times two actors chose one another and/or both chose the same third actor). The matrix of agreements was converted into a matrix of correlations and a factor analysis was performed on that matrix.
Proctor used the results of the factor analysis to partition the families into groups. Each of the first seven factors was strongly associated with a different subset of families. Each of these seven factors was used to define a "clique" of families that were linked together. Figure 14 was produced by arranging the members of each "clique" into a circle and placing the seven circles in arbitrary locations in the page.
Figure 14. "Cliques" of Families in Atirro, Costa Rica.
Figure 15. Clusters of School Children (Bock and Husain, 1952).
-
The earliest use of computational procedures in producing point and line diagrams all focused on the problem of determining locations for the points. Bock and Husain (1952) and Proctor (1953) were the first to report using computational procedures to aid in placing points. They both used factor analysis, but produced very different kinds of images.
-
later investigators picked up on Lundberg and Steele's idea of varying the sizes of points in order to emphasize their differences in sociometric status.
-
Chapin (1950), developed a very early three-dimensional display of social network data. He began with the data from the lady bountiful diagram and built an apparatus that showed the social status, the outdegree and the indegree of every point. In Figure 10 the vertical dimension is social status, the horizontal one is outdegree and the one running in and out is indegree. Chapin argued that the center points of Figure 9 are really isolates and should be displayed as such.
-
Figure 9. The "Lady Bountiful."
Figure 10. Apparatus for the Display of the Data of Figure 9.
Figure 11. A Target Sociogram.
-
constructed their famous "lady bountiful" image by making the nuclei larger than other points and by placing them near the middle of their drawing. Then they arranged the points representing actors who were chosen less often in circles around the nuclei. See Figure 9 where the number associated with a point is based on an index of the social class of the actor represented by that point.
-
investigators began to introduce innovations designed to extend Moreno's general approach in ways that would emphasize structural features of special interest to them. One structural feature that was of great interest to early investigators was the sociometric status of each point. The sociometric status of a point was defined as the number of choices, or the strength of the choices, received by that point. Investigators thought that this might be a good index of power or influence.
-
Lundberg and Steele (1938), for example, specified the nuclei of a network as those actors with high sociometric status.
-
Figure 6. A Nautical Food Web.
Figure 7. Visiting Patterns among Households.
Figure 8A. A Map of Russian River Trade Routes.
Figure 8B. A Graph of Russian River Trade Routes.
-
In most point and line displays the points represent social actors and the lines represent connections among the actors. I
-
Moreno introduced five important ideas about the proper construction of images of social networks: (1) he drew graphs, (2) he drew directed graphs, (3) he used colors to draw multigraphs, (4) he varied the shapes of points to communicate characteristics of social actors, and (5) he showed that variations in the locations of points could be used to stress important structural features of the data.
-
He combined both liking and disliking in a single multigraph in which he used color to show both relations in the same picture.
-
Boys are shown as triangles and girls as circles.
-
The different shapes and the placement of points show dramatically the segregation of choices by gender. In fact, only one boy chose a girl and no girl chose any boy as a friend.
-
The data are friendship choices
-
He used variations in both the locations and the shapes of points to convey additional information about the structural properties of social networks.
-
It should also be noted that there are no crossing lines either in Figure 1 or Figure 2. Later, Moreno (1953, p.141) specified this idea as a general rule for constructing sociograms. He said, "The fewer the number of lines crossing, the better the sociogram." This rule is still widely used.
-
This kind of drawing is called a directed graph. It reveals important structural features of the data. Baby A for example was seemingly at the bottom of some sort of hierarchy of recognition; it was not recognized by any of the others. In contrast, B, D, G and H were at the top; each was recognized by two others. And C, E, F and I were in the middle; each was recognized by one other. But the hierarchy is far from strict; C and E recognized each other, and G, H and I formed a cycle in which G recognized I, I recognized H and H recognized G.
-
Very soon Moreno (1934) generalized this approach. He suggested that there might be a directed relation linking two actors A and B. Suppose, for example, that A reports responding to B while B does not respond to A. In such cases Moreno suggested drawing a directed line -- one with an arrowhead -- from the point representing A to the one representing B. Then if each responded to the other (see C and E in Figure 2), he proposed drawing a line without arrowheads (but with a small crossing line splitting the line connecting the pair).
-
A graph consists of a set of points along with a set of lines connecting pairs of points.
-
nd some images manage to reveal a good deal about both groups and positions at the same time.
-
Other images stress similarities and differences in the positions occupied by actors.
-
Some images are constructed in such a way that they emphasize important features of group structure.
-
seek to uncover either or both of two kinds of patterns. They often look for social groups -- collections of actors who are closely linked to one another. Or, alternatively, they look for social positions -- sets of actors who are linked into the total social system in similar ways.
-
Network analysts study the patterning of the social connections that link sets of actors.
-
Although a good many investigators innovated in introducing new point shapes, a far more common concern has been with the question of how to locate the points on the page. Moreno's idea (shown in Figure 4) of placing points in positions that map to their actual locations in physical space has been widely used, particularly by rural sociologists and by geographers.
-
-
14 Oct 06
Gary BurgeThe paper reviews the long history of image use in the field. It begins with illustrations of the earliest hand-drawn images in which points were placed by using ad hoc rules. It examines the development of systematic procedures for locating points. It go
-
16 May 06
-
14 Feb 05
-
Visualizing Social Networks Linton C. Freeman University of California, Irvine ABSTRACT: This paper documents the use of pictorial images in social network analysis. It shows that such images are critical both in helping investigators to understand network data and to communicate that understanding to others. The paper reviews the long history of image use in the field. It begins with illustrations of the earliest hand-drawn images in which points were placed by using ad hoc rules. It examines the development of systematic procedures for locating points. It goes on to discuss how computers have been used to actually produce drawings of networks, both for printing and for display on computer screens. Finally, it illustrates some of the newest procedures for producing web-based pictures that allow viewers to interact with the network data and to explore their structural properties.
-
Would you like to comment?
Join Diigo for a free account, or sign in if you are already a member.