Social Network Analysis (4.3 out of 5 stars)

Note: This post represents the synthesis of the thoughts, procedures and experiences of others as represented in the  articles read in advance (see previous posts) and the discussion among the students and instructor during the Advanced Analytic Techniques class at Mercyhurst University in November 2015 regarding Social Network Analysis as an Analytic Technique specifically. This technique was evaluated based on its overall validity, simplicity, flexibility and its ability to effectively use unstructured data.

Description:

Social Network Analysis (SNA) is a methodology in that the mathematical assessment of a network will produce an estimate, typically involving which are the most important or influential nodes. This technique involves the examination and assessment of a network, which is composed of individuals (nodes) and their relationships (ties). Utilizing this type of analysis, a visualization of the network can be developed. SNA can be used to determine the robustness and efficiency of a network, and can therefore be used to move information through the network or destroy the network all together.

Strengths:

• Can provide a holistic picture of a network
• Maps the spread of ideas and can determine who is the most influential individual(s) in a network
• Provides an alternative view where attributes of individuals are less important than their relationship ties
• It is highly quantitative and mathematically valid
• SNA in a matrix form can provide a quantitative score of relationships, although it will have bias associated with it.
• Identifies the type of network they are analyzing: centralized or decentralized
• Can help analysts identify the most powerful nodes in a network
• Can be used to simulate how information ripples through a network
• Can be used to identify intelligence gaps

Weaknesses:

• This tool can only be used in some situations, not all cases are applicable for social network analysis
• Defining relationships and understanding what that relationship means is difficult
• Visualization does not always tell a clear story therefore making it difficult to communicate to a DM
• Only allows for one relationship between two people to be defined, so it must be defined carefully
• SNA for ambiguous organizations may cause confirmation bias
• Constructing a matrix can be time consuming
• Matrix attributes can be subjective and often biased

How-To:

• Step 1: Identify a pattern of relationships or lines of communication you want to analyze. In other words, identify a possible network for further exploration.
• Step 2: Input all members of this group/network/etc into a matrix. On the left side will have all members who initiate communication and on the top will be all receivers of communication.
• Step 3: Score the relationships on whatever scale you deem fit. Example: (Joe talks to Maria, that communication for Joe is a score of 5. His communication to his enemy may be a -5.) The highest scores of all the rows would be members that would be key nodes and members would be considered the main communicators. The highest scores at the bottom are the members who receive the most information/communication.
• Step 3: Input the data (matrix) into a software program to generate the network map. On a small-scale individuals can draw out the map based on the matrix or via known dialogue/intelligence.
• Step 4: Based on the matrix and the visual network map, identify the key relationships and the strongest communication nodes.

Personal Application of Technique:

Practical Exercise 1

For this exercise, we used four people to establish a small network flow focused on the flow of information. The four people were: Professor Wheaton, Andrew, Dan, and Katie.

1.   Design a map based on the following communications:

• Prof. Wheaton: Andrew, go tell Dan & Katie to meet tonight for a super secret meeting.
• Andrew: Katie, make sure Dan gets to the meeting.
• Andrew: Dan, you & Katie better be at the super secret meeting.
• Prof. Wheaton: Katie, did Andrew tell you about the super secret meeting?
• Dan: Hey Katie, we have a super secret meeting to go to.

2.  Make a matrix

Relationships:

Prof. Wheaton: project leader, not a micro-manager

Andrew: asst. project leader, more of a micro-manager

Dan: team member, friends with Andrew

Katie: team member

Practical Exercise 2: Family SNA

1. Imagine big news in your family and how news would spread

2. Pick 4 to 5 people to assess the network

3. Draw the network map

4. Draw the matrix

5. Fill it in & scoring it based on your knowledge of personal relationships

Dynamic Spread of Happiness in a Large Social Network

By: James H. Fowler and Nicholas A Christakis

Summary:

Happiness is a fundamental object of human existence to the point that the World Health Organization emphasizes happiness as a component of health.  A large variety of voluntary and involuntary factors determines a person’s happiness.  Emotional states can be “caught” or transferred directly from one individual to another in many different ways.  This study looked at how happiness spreads over long periods through a social network in both direct relationships and indirect ones (i.e. friends of friends) as well as whether there were geographical or temporal constraints on this spread through the network.

Looking at 5,124 individuals – deemed “egos” – each connected to others via friendship, family, marriage, coworkers, or geographically.  Each person who had a relationship with an ego – deemed an “alter” – brought the totally participants up to 12,067 studied individuals.  There were 53,228 observed social ties between 5,124 egos and alters, averaging 10.4 ties to family, friends, and coworkers.  Though there were substantial variations from person to person, with some egos ranging from several people with no friends to one person who was nominated as a friend by eight different participants.  The 3 types of defined friendship are the “ego perceived friend,” the “alter perceived friend,” and the “mutual friend.”  The first being the alter thinks of the ego as a direct friend, the second being the ego thinks an alter as a friend, and the last being both the ego and the alter consider themselves friends.

The study defines happiness as a positive emotion used a conventional measure using 4 items from the CES-D (Center for Epidemiological Studies depression scale) in which people were asked how often they experienced certain feelings during the previous week.  Happiness was considered a perfect score on each of the 4 items, but close to perfect results was also recognized and weighed.  The social network consists of the individuals (nodes) and relationships (social ties) between them.  Once all the nodes and ties are known, a picture can be drawn of the network to discern position within it. 

Examination of the social network indicated that happy people tend to be connected to one another.  The below figure mapped the largest connected network in 1996 and 2000 based on a restricted set of ties among siblings, spouses, and friends.  Each node is colored according to a person’s happiness on a spectrum from blue (unhappy) to green (intermediate) to yellow (happy).

The clusters of happy and unhappy people seen in the network are significantly larger and calculable.  The relationship of an ego and alter’s happiness is calculable by measuring the probability that an ego is happy when an alter is happy and comparing it to the same probability in a simulated network.  This data also suggests a relation between network centrality and happiness as people at the core of their local networks are more likely to be happy.  It should be noted that happiness itself does not increase one’s centrality at subsequent time points.

Critique:

While there are many determinants of happiness, whether an individual is happy also depends on whether others in the individual’s social network are happy.  Happiness is not just a function of individual experience or choice, but is also a property of groups of people.  Social network analysis makes it possible to visualize the changes and ripple effects through a network to generate large scale structures and identify clusters within a network.  I found these results interesting considering that happiness generally requires close physical proximity to spread and that the effect decays over time.  Nonetheless, the analysis does not allow for the actual cause of happiness (or other emotions) to be identified.  It also recognizes that while the person to person effects tend to be string, they decay throughout the network so a particular mood or behavior ripple is very limited. 

Source:

BMJ 2008; 337 doi: http://dx.doi.org/10.1136/bmj.a2338 

(Published 05 December 2008)

Cite this as: BMJ 2008;337:a2338

Advocating for the Use of Social Network Analysis in Individual Psychology

Curlette, W. L., & Hendrick, R. C. (2015). Advocating for the Use of Social Network Analysis in Individual Psychology. The Journal of Individual Psychology, 71(1), 75-85.

http://muse.jhu.edu/login?auth=0&type=summary&url=/journals/the_journal_of_individual_psychology/v071/71.1.curlette.html

Summary:

The primary focus of this article is to show the potential social network analysis has in the field of Individual Psychology.  The article states that research employing quantitative methods for social network analysis in Individual Psychology has not been published in The Journal of Individual Psychology, and that it is unlikely social network analysis work has been published in any other journal in the field either.  They cite the University of Twente website when describing social network analysis, Network analysis (social network theory) is the study of how the social structure of relationships around a person, group, or organization affects beliefs or behaviors.  The authors also state that, although social network analysis focuses on relationships between actors, characteristics of actors in the network can be related statistically to measures of the network.

The quantitative methodology laid out by the authors as a general example of social network analysis starts with a questionnaire given to the group in question.  Based on the responses to that questionnaire, in regards to the frequency and nature of their relationships with others, a square matrix can be generated.  This matrix will show in numeric terms who is communicating in the group being examined.  The specificity of the information in the matrix can be improved by carefully shaping the questions on the survey to take into consideration the characteristics of the people on the list, examples are what organization they work for or what country they are from.  The authors believe that an area for the application of social network analysis in Individual Psychology is the study of Gemeinschaftsgefuhl, which has been translated as "social interest". 

The section “Data Analysis for the Social Networks” provides a good overview of social network analysis.  It refers back to the matrix that was mentioned earlier and how it allows for the creation of dichotomous responses as well as the frequency or strength of communication.  Eight measure are employed for describing social networks:

1. Size of the matrix – number of rows or number of columns
2. Density – there are various definitions, including number of ties in matrix of dichotomous responses as a proportion of total number of possible ties
3. Reciprocity - proportion of actors selecting one another, with the highest possible value being 1.0
4. Transitivity - relationships between triads of actors, which can indicate the degree of stability and consistency of the network
5. Diameter - number of steps in the longest path connecting two actors, which can indicate how resources are transferred
6. Distance - mean path length between all pairs of actors
7. Clustering - areas of dense connections between actors
8. Centralization - high centralization occurs when a small number of actors are the focus of many relations, which indicates both how resources are distributed across the network and a high concentration of power and control

Comparing two networks can be done descriptively or by using the Quadratic Assignment Procedure (QAP).  The QAP is a resampling approach using Monte Carlo methods.

The best example given in the article involved the analysis of HIV and HPV research on an international scale.  The countries in which the research was published are the nodes and all the information was presented as a graph.  The US had the most research, therefore the USA node is the largest.  The width of the connections indicates the number of collaborations between any two countries.  This is just one example, the nodes could easily be organizations, schools, or families.

Critique:

From the prospective of trying to educate an unfamiliar audience with the possibilities and capabilities of social network analysis this article is very successful.  The underlying principles of social network analysis were laid out in the methodical and easy to read format.  In terms of adding to the overall field of Individual Psychology this article does little.  All that is really accomplished by the authors is that they have shown that social network analysis is a methodology which will work with Individual Psychology, and provide a few examples of analysis that could potentially be done.  

Social Network Analysis in the Study of Terrorism and Political Violence

Arie Perliger & Ami Pedahzur, 2010

Summary

Social Network Analysis (SNA) in the study of political violence has remained quite limited, and still amounts to only a small fraction of the research in the field due to the fact that the majority of political violence students have very limited acquaintance with the rationale, and the main concepts and methodological tools of SNA. Since September 11th, growing numbers of media outlets and the striking increase in the efforts and resources invested in data collection (for example, START at the university of Maryland and TIGER at the University of Texas at Austin), have simplified the adaptation of research methods which demands high resolution information about the terrorists and their groups, among them SNA. However, many of the researchers are still reluctant to exercise SNA in their studies and consequently tend to express doubt regarding its efficiency and relevance for the study of complex social phenomena.

How to Study Violent Social Networks

Naturally, in the case of terrorist groups, researchers strive to include all the actors who take part in the group’s activities and the social processes leading to the violent activities. However, this raises the question of what constitutes significant participation in these processes. A more inclusive perspective would involve all those who assisted in the execution of the attacks. This includes actors who were part of the group for short time, individuals who were not present in the formation stages of the group yet did not participate in the decision-making processes, or spiritual leaders who just provided moral support for the actual perpetrators. By contrast, an exclusive outlook would include only actors who are longtime members of the group, participating consistently in its activities and in the decision-making processes, and who have continuous relations with other members. The inclusive approach better fits mapping the network in its initial stages. However, exclusive approach will provide more valid representation of the network in the operational stages of its activities. After deciding which actors belong to the network, a decision must be made regarding the categorizations of tie types. While ties may have different characteristics—they can be binary or not, symmetrical or asymmetrical (even strength in both directions or stronger in one direction), negative or positive—it seems that measuring tie strength is most relevant for understanding the social dynamic within violent networks.

One of the main advantages, which SNA provides for researchers of terrorists groups, is the capability to uncover the informal division of influence and social capital within the group, which, in turn, influences the group’s internal political and social processes and the outcome of its activities. Besides, it also helps to better understand the motives beyond the group’s actions. A high number of ties is not the only criteria for detecting informal leaders. The actors who are in strategic locations and serve as connectors between the different subgroups possess significant power and are crucial for the survival of the network. While they do not have to be connected to high numbers of members, they can veto almost any operation that needs the cooperation of the different subgroups. Besides, there are those who do not have a particularly large number of ties, nor are they connectors between different parts of the network, but they are situated in a strategic location in terms of their proximity to hubs or to large numbers of members within the network; hence, they have high level of access to information and resources. Some of the prominent relevant measures, which can be effective in the study of violent groups, are degree of centrality, closeness and betweenness. Identifying the subgroups is also crucial point. It allows us to detect different functions of the network (founders, collaborators, passersby), network recruitment paths, operational characteristics and patterns of flow of information.

Since we can assume that actors’ behaviors are a product of their structural opportunities and constraints, we can expect actors with similar location characteristics to react in similar ways. Thus, SNA could be of high value for understanding the relations between different terrorist groups worldwide.

Critique

The article illustrates the potential of SNA in the study of political violence and terrorism.  This method can be highly useful for further developing and testing some of the current prominent theoretical frameworks in the field. However, the article does not give a deep insight. It just gives an overall idea about how to conduct SNA in political violence and terrorism domain.

Source:

Perliger, Arie and Pedahzur, Ami, "Social Network Analysis in the Study of Terrorism and Political Violence" (2010). Working Papers. Paper 48.

http://opensiuc.lib.siu.edu/pn_wp/48

Social Network Analysis - Theory and Applications

By: Dr. David L. Passmore - PennState

Summary:

A Social network is a social structure made up of individuals or organizations called “nodes”, which are connected by one of more specific types of inter-dependency, like friendship, kinship, common interest, financial obligations, sexual relationships, or beliefs.

Social network analysis (SNA) views social relationships in terms of network theory consisting of nodes and ties. Nodes are the individuals within the network, and ties are the relationships that connect the actors. There can be many kinds of ties between the nodes, and research has shown that social networks operate on a many different and complex levels. A social network is a map of specified ties between nodes being studied. The nodes to which an individual is connected are the social contacts of that individual. The network can also be used to measure social capital, the value that an individual receives from the social network. These relationships are often displayed in a social network diagram, where nodes are the points and ties are the lines.

SNA has now moved from being a suggestive metaphor to an analytic approach to a paradigm, with its own theoretical statements, methods, social network software, and researchers. Analysts reason from the whole to part, from structure to relation to individual, and from behavior to attitude. The power of social network analysis stems from its difference from traditional social scientific studies, which assume that it is the attributes of individual actors that matter. SNA produces an alternate view, where attributes of individuals are less important than their relationships and ties with other actors within the network. This approach has turned out to be useful for explaining many real-world phenomena, but leaves less room for the ability of individuals to influence their success. 

SNA has been used in a variety of research fields, and is an effective tool for mass surveillance. The Total Information Awareness program was doing in-depth research on strategies to analyze social networks to determine whether or not certain citizens were political threats. Diffusion of innovations theory explores social networks and their role in influencing the spread of new ideas and practices.

Measures used in SNA:

Betweenness - The extent to which a node lies between other nodes in the network. This measure takes into account the connectivity of the node's neighbors, giving a higher value for nodes which bridge clusters. The measure reflects the number of people who a person is connecting indirectly through their direct links. 

Bridge - An edge is said to be a bridge if deleting it would cause its endpoints to lie in different components of a graph. 

Centrality - This measure gives a rough indication of the social power of a node based on how well they "connect" the network. "Betweenness", "Closeness", and "Degree" are all measures of centrality.

 

Centralization - The difference between the number of links for each node divided by maximum possible sum of differences. A centralized network will have many of its links dispersed around one or a few nodes, while a decentralized network is one in which there is little variation between the number of links each node possesses.

 

Closeness - The degree an individual is near all other individuals in a network (directly or indirectly). It reflects the ability to access information through the "grapevine" of network members. Thus, closeness is the inverse of the sum of the shortest distances between each individual and every other person in the network. The shortest path may also be known as the "geodesic distance".

 

Clustering coefficient - A measure of the likelihood that two associates of a node are associates themselves. A higher clustering coefficient indicates a greater 'cliquishness'.

 

Cohesion - The degree to which actors are connected directly to each other by cohesive bonds. Groups are identified as ‘cliques’ if every individual is directly tied to every other individual, ‘social circles’ if there is less stringency of direct contact, which is imprecise, or as structurally cohesive blocks if precision is wanted.

 

Degree - The count of the number of ties to other actors in the network. 

 

Flow betweenness centrality - The degree that a node contributes to sum of maximum flow between all pairs of nodes (not that node).
 

Eigenvector centrality - A measure of the importance of a node in a network. It assigns relative scores to all nodes in the network   based on the principle that connections to nodes having a high score contribute more to the score of the node in question.

 

Local bridge - An edge is a local bridge if its endpoints share no common neighbors. Unlike a bridge, a local bridge is contained in a cycle.

 

Path length - The distances between pairs of nodes in the network. Average path-length is the average of these distances between all pairs of nodes.

  

Prestige - In a directed graph prestige is the term used to describe a node's centrality. "Degree Prestige", "Proximity Prestige", and "Status Prestige" are all measures of Prestige. 

Radiality - Degree an individual’s network reaches out into the network and provides novel information and influence.

 

Reach - The degree any member of a network can reach other members of the network.

Structural cohesion - The minimum number of members who, if removed from a group, would disconnect the group.

Structural equivalence - Refers to the extent to which nodes have a common set of linkages to other nodes in the system. The nodes don’t need to have any ties to each other to be structurally equivalent.

 

Structural hole - Static holes that can be strategically filled by connecting one or more links to link together other points. Linked to ideas of social capital: if you link to two people who are not linked you can control their communication.  

Example of SNL

 

Critique:

The source I used to summarize the article was extremely long, and I attempted to capture the basics of SNA to provide an introduction to the technique. I would recommend those interested to browse the PDF for more details, as the author describes different typologies of SNA, and provides a list of software that can be used.

In the intelligence field, SNA is extremely useful on the tactical level in a non-conventional military setting. I have unwittingly used this methodology downrange on i2. The way I applied SNA was by building connections to known Taliban members, which resulted in visual representations how several cells (groups) operated within our AOR (Area of Operations). Within each cell the leader was identified, and his connections to higher tier targets. With the information I was able to produce target packages, which our companies used to capture or kill HVTs (high value targets). The information I provided is vague (and sanatised), and other methods were used in conjunction with SNA, but were not described for OPSEC (operational security) purposes.

Source: http://train.ed.psu.edu/WFED-543/SocNet_TheoryApp.pdf