A social network analysis of research collaboration in physics education

A social network analysis of research collaboration in physics education
Based on the author indices over the past ten years in three international journals of physics teaching, we have constructed networks of physics educators. The latter are connected if they have published one or more articles together in any one of the three journals. We obtained some important sociological characteristics of the research collaborations or linkages between physics teachers. These results indicate how experiences, ideas, and methods are shared, the degree of collaboration, the existence of clusters between physics teachers, and the productivity distribution. Many aspects of our results differ significantly from those recently found by other researchers on the co-authorship networks of scientists in various fields. The present work can serve as an example of the application of the concepts and features of social network analysis. © 2005 American Association of Physics Teachers

from - http://ajp.aapt.org/resource/1/ajpias/v73/i2/p145_s1?isAuthorized=no

Network Analysis in the Social Sciences

Network Analysis in the Social Sciences
Over the past decade, there has been an explosion of interest in network research across the physical and social sciences. For social scientists, the theory of networks has been a gold mine, yielding explanations for social phenomena in a wide variety of disciplines from psychology to economics. Here, we review the kinds of things that social scientists have tried to explain using social network analysis and provide a nutshell description of the basic assumptions, goals, and explanatory mechanisms prevalent in the field. We hope to contribute to a dialogue among researchers from across the physical and social sciences who share a common interest in understanding the antecedents and consequences of network phenomena

from - http://www.sciencemag.org/content/323/5916/892.short

A Marketer’s Introduction to Social Network Analysis

For many, Social Networks begin and end with Social Media, but network analysis is about much more than tweeting.   As the tools improve, Social Network Analysis will become as important to marketing as target group analysis was a generation ago.

Understanding networks will help us bring order to the complexity and chaos in the world around us.   From how information spreads to managing sales and finding the information we need, networks can help us run our businesses better.

Fortunately, all you really need to know about networks, social or otherwise, you can learn on your next airline flight.
The Importance of Hubs
On your next trip, once you have paid strict attention to the safety procedures, take a look at the airline magazine in the seat pocket in front of you.   If you open it to the back, you will find a map of showing all the airports your airline flies to with paths between them designating routes.
If you take some time and start counting, you will see a pattern develop.   The biggest airport will have roughly twice as many routes leading to it as the second biggest airport, three times as many as the third biggest airport and so on.  The bigger the airline you are flying on, the closer these proportions will hold.
Mathematicians call this proportional scaling. They denote the relationship as 1/s and it holds for many naturally occurring phenomena, such as income and population distributions, amazon.com sales, ecological systems, etc.  It has a distinctive shape that Chris Andersen made famous as the long tail.
Another point of interest is the overall proportions. With some more checking you will find that roughly 20% of the airports account for about 80% of the routes.  Over a century ago, Vilfredo Pareto recognized this pattern in economic data.  Many managers know that this 80/20 rule also holds for their businesses as well.
You don’t have to look very deeply to see that much of our world works like an airline map.



Anti-Hub Strategy – The Case for Efficient Network Paths
When we travel, we want to choose the most efficient network path.  Our airline travel is just a means to an end so we want to spend as little time and money as we can on it. The airlines share some of our concerns but not all.
Some airlines choose a hub strategy.  They have strong presences at major airports such as London Heathrow, Chicago O’Hare and others.   Through investing in these hubs they are betting their ability to take us to all the places we want to go will be valuable enough to us for them to make a nice profit.
Others, like Southwest and Ryan Air, choose a different strategy altogether.  For the most part, they bypass hubs and can’t take us everywhere we want to go.   However, for the places they can take us they can do so very cheaply.
The Benefits of a Robust Network
We have the best situation of all, because we know exactly where we want to go. If a well traveled route takes us to a preferred destination, chances are that we will find a very cheap flight. If not, we can go through hubs and still get to where we want to go. In either case, travel agents have software with fairly simple algorithms that will help us find the most efficient network path.
The richer and more diverse the network, the bigger the hubs will be and also the more ways around them. Well traveled routes will give us a variety of options, while more out of the way places will inevitably cost more.
We see the same thing in business.  For many products, we can just market to the masses very cheaply and the customer network will do the rest. We can even help the process along by encouraging people to forward our message through social media. (See How Ideas Spread)
However, some products are niche and require us to spend more by targeting specific network paths through trade and event marketing.
Evaluating Networks
If you page back in your airline magazine a bit, you will find the “feature well” with some longer articles for your reading enjoyment.  If you have some time, you can make a list of the words in each article and how many times they appear and you will find that the mathematics of networks apply here too.
Once you have finished, you might notice the same thing that George Zipf did in 1932.  The distributions of words follows the same 1/s law that holds for airline routes and amazon.com sales. In effect, language also follows network laws.
However, texts are a bit different because they are evaluated holistically.  It is natural to speak of good writers and bad writers and word distributions can give us a clue to discern between the two. Better writers usually have wider vocabularies and therefore have wider word distributions in their texts.  The wider the choice of paths, the more ways to gain efficiency of expression.
While it is common to think of written texts this way, it is also true of anything that follows network rules.  For instance, we like Amazon because it gives us a lot of efficient network paths.   Just like a great writer has the vocabulary to find the perfect word, we can usually find just what we’re looking for on Amazon.
To see how we can apply this simple rule to any business, here’s an example of two different businesses with approximately the same revenues
As you can see, the sales follow the familiar “long tail” pattern. A small amount of customers spend a lot, and a lot of customers spend a little.
Due to a algebraic quirk, we can evaluate networks mathematically quite easily.  With a fairly simple technique called a log-log plot, we can transform our network from a hard to work with “long tail” to a simple downward sloping linear graph that we used in high school.
Moreover, just like in high school we can evaluate the curve by taking the rise over the run.   The smaller the value of our slope, the wider the revenue distribution, the more complex interactions and the more robust the network is.
If we apply the same technique to our two businesses, we can see that our two “long tails” are actually quite different
Here, we can clearly see that while business A is more reliant on big customers, Business B has a more diverse customer base, even though they have roughly the same sales and number of clients. Moreover the slope give us a good numerical way to rank diversity: the flatter the slope the more diverse the revenue sources are .
While the math might seem complicated, it’s actually pretty easy to set up an excel template to calculate everything.
How Networks Grow
Lets take another look at word distributions.  We’re not born with a full vocabulary, we have to learn each word.
When we were young, our parents were delighted to hear our first word.  Eventually, our vocabulary became richer and we learned different categories of words.  Simple words we use a lot and it would be tough to communicate without them. Other words are used much less but can take on greater importance depending on context.
It really doesn’t matter where we start our network journey because we can always add new connections.  Einstein was a late talker – in German – but later became highly respected for the things he said in English. Facebook didn’t start at a party school, but at Harvard.
There hasn’t been a marketing strategy invented that’s a match for happy customers and word of mouth.  Brand networks grow through the the people who are devoted to them.  Given enough passion, anybody can be an “Influential.”
Network Marketing Applications
In business, we will find three common applications:
Robustness: By measuring the diversity of a network, we can get a good idea how strong it is. A business that is based on a few hubs is more vulnerable to external shocks.
Broadcast: In order to sell our wares and make money, we need to get our message out.  The connections in networks help us to do that. Moreover, just like a worldwide tour can start in any city and a sesquipedalian’s vocabulary can start with any word we have a variety of ways to broadcast.
In effect, we want to find the most efficient network path. Hubs are useful, but we don’t want to overpay.  The real issue best strategy will allow us to cover the network most efficiently, which requires us to not only consider hubs but also paths around them.
Targeting: As mentioned above, networks are rich in information contained both in objects and in the connections between them.   Whenever we need information, chances are that we have access to a network that contains it. Targeting is the converse of broadcast because we want to narrow the paths rather than maximize them.  In effect, it is a search.
The key with a network search is to not make it too broad by trying to search an entire network and not make it too narrow by using too many parameters.  Experimentally it has been shown that two or three parameters is enough to perform an efficient search. Any more than that and we will most probably exclude valuable network paths that could lead us to our destination efficiently. (See Social Search)
This issue will come to the fore as digital marketing becomes more pervasive.   Just because we can exclude people doesn’t mean we should. We’ll need to be careful not to over-target.
Using Network Theory to Help Form a Marketing Strategy
The more varied our customer base, the more stable our business will be and the less vulnerable to market shocks.   If we find that our customer base is lagging behind our competitors, that’s a good sign that we need to go after new segments.
Another key point is that we want to find the most efficient way to reach our goals.  That might not always be the most targeted or the most direct.   We can often initiate more network paths cheaper through a mass audience.
Just like when we go to a travel agent, there are lots of things to confuse us.   Fancy travel posters of exotic locations, frequent flyer deals and other gimmicks shouldn’t change the simple fact that we want to go somewhere quickly, cheaply and with some comfort.
Fortunately, just like with our travel plans, we can navigate the networks that are crucial to business with a little information, some common sense and a good idea of where we want to go.

2010 Social Network Analysis Report – Geographic – Demographic and Traffic Data Revealed

2010 Social Network Analysis Report – Geographic – Demographic and Traffic Data Revealed
Its that time of the year again and I thought our readers would be curious how the different social networks have progressed over the last 2 years since we started analyzing the various social networks from around the world. It is interesting to note that the domain type in traffic has fallen for almost all of the social networks we analyzed. We are not sure if this is an anomaly with the Google Insights for Search tool, or if users are realizing you don’t need to Google domain.com, you simply need to use the browser for what it was intended for. In any case, I have highlighted some of the changes below. Remember all insight is gathered from Google Ad Planner and Google Insights for Search

from - http://www.ignitesocialmedia.com/social-media-stats/2010-social-network-analysis-report/

Social Network Analysis and Mining

The rapid increase in the interest in social networks has motivated the need for a more specialized venues with wider spectrum capable of meeting the needs and expectations of a variety of researchers and readers. Social Network Analysis and Mining (SNAM) is intended to be a multidisciplinary journal to serve both academia and industry as a main venue for a wide range of researchers and readers from social sciences, mathematical sciences, medical and biological sciences and computer science. We solicit experimental and theoretical work on social network analysis and mining using different techniques from sociology, social sciences, mathematics, statistics and computer science. The main areas covered by SNAM include: (1) data mining advances on the discovery and analysis of communities, personalization for solitary activities (like search) and social activities (like discovery of potential friends), the analysis of user behavior in open forums (like conventional sites, blogs and forums) and in commercial platforms (like e-auctions), and the associated security and privacy-preservation challenges; (2) social network modeling, construction of scalable, customizable social network infrastructure, identification and discovery of dynamics, growth, and evolution patterns using machine learning approaches or multi-agent based simulation. Papers should elaborate on data mining or related methods, issues associated to data preparation and pattern interpretation, both for conventional data (usage logs, query logs, document collections) and for multimedia data (pictures and their annotations, multi-channel usage data).
Topics include but are not limited to:

• Web community
• Personalization for search and for social interaction
• Recommendations for product purchase
• information acquisition and establishment of social relations
• Recommendation networks
• Data protection inside communities
• Misbehaviour detection in communities
• Preparing data for web mining
• Pattern presentation for end-users and experts
• Evolution of communities in the Web
• Community discovery in large-scale social networks
• Dynamics and evolution patterns of social networks, trend prediction
• Contextual social network analysis
• Temporal analysis on social networks topologies
• Search algorithms on social networks
• Multi-agent based social network modeling and analysis
• Large-scale graph algorithms
• Applications of social network analysis
• Anomaly detection in social network evolution

from - http://www.springer.com/computer/database+management+%26+information+retrieval/journal/13278

Social Network Analysis, A Brief Introduction

from- http://www.orgnet.com/sna.html

Social Network Analysis, A Brief Introduction

Social network analysis [SNA] is the mapping and measuring of relationships and flows between people, groups, organizations, computers, URLs, and other connected information/knowledge entities. The nodes in the network are the people and groups while the links show relationships or flows between the nodes. SNA provides both a visual and a mathematical analysis of human relationships. Management consultants use this methodology with their business clients and call it Organizational Network Analysis [ONA].
To understand networks and their participants, we evaluate the location of actors in the network. Measuring the network location is finding the centrality of a node. These measures give us insight into the various roles and groupings in a network -- who are the connectors, mavens, leaders, bridges, isolates, where are the clusters and who is in them, who is in the core of the network, and who is on the periphery

We look at a social network -- the "Kite Network" above -- developed by David Krackhardt, a leading researcher in social networks. Two nodes are connected if they regularly talk to each other, or interact in some way. Andre regularly interacts with Carol, but not with Ike. Therefore Andre and Carol are connected, but there is no link drawn between Andre and Ike. This network effectively shows the distinction between the three most popular individual centrality measures: Degree Centrality, Betweenness Centrality, and Closeness Centrality.

Degree Centrality

Social network researchers measure network activity for a node by using the concept of degrees -- the number of direct connections a node has. In the kite network above, Diane has the most direct connections in the network, making hers the most active node in the network. She is a 'connector' or 'hub' in this network. Common wisdom in personal networks is "the more connections, the better." This is not always so. What really matters is where those connections lead to -- and how they connect the otherwise unconnected! Here Diane has connections only to others in her immediate cluster -- her clique. She connects only those who are already connected to each other.

Betweenness Centrality

While Diane has many direct ties, Heather has few direct connections -- fewer than the average in the network. Yet, in may ways, she has one of the best locations in the network -- she is between two important constituencies. She plays a 'broker' role in the network. The good news is that she plays a powerful role in the network, the bad news is that she is a single point of failure. Without her, Ike and Jane would be cut off from information and knowledge in Diane's cluster. A node with high betweenness has great influence over what flows -- and does not -- in the network. Heather may control the outcomes in a network. That is why I say, "As in Real Estate, the golden rule of networks is: Location, Location, Location."

Closeness Centrality

Fernando and Garth have fewer connections than Diane, yet the pattern of their direct and indirect ties allow them to access all the nodes in the network more quickly than anyone else. They have the shortest paths to all others -- they are close to everyone else. They are in an excellent position to monitor the information flow in the network -- they have the best visibility into what is happening in the network.

Network Centralization

Individual network centralities provide insight into the individual's location in the network. The relationship between the centralities of all nodes can reveal much about the overall network structure.
A very centralized network is dominated by one or a few very central nodes. If these nodes are removed or damaged, the network quickly fragments into unconnected sub-networks. A highly central node can become a single point of failure. A network centralized around a well connected hub can fail abruptly if that hub is disabled or removed. Hubs are nodes with high degree and betweeness centrality.
A less centralized network has no single points of failure. It is resilient in the face of many intentional attacks or random failures -- many nodes or links can fail while allowing the remaining nodes to still reach each other over other network paths. Networks of low centralization fail gracefully.

Network Reach

Not all network paths are created equal. More and more research shows that the shorter paths in the network are more important. Noah Friedkin, Ron Burt and other researchers have shown that networks have horizons over which we cannot see, nor influence. They propose that the key paths in networks are 1 and 2 steps and on rare occasions, three steps. The "small world" in which we live is not one of "six degrees of separation" but of direct and indirect connections < 3 steps away. Therefore, it is important to know: who is in your network neighborhood? Who are you aware of, and who can you reach?
In the network above, who is the only person that can reach everyone else in two steps or less?

Boundary Spanners

Nodes that connect their group to others usually end up with high network metrics. Boundary spanners such as Fernando, Garth, and Heather are more central in the overall network than their immediate neighbors whose connections are only local, within their immediate cluster. You can be a boundary spanner via your bridging connections to other clusters or via your concurrent membership in overlappping groups.
Boundary spanners are well-positioned to be innovators, since they have access to ideas and information flowing in other clusters. They are in a position to combine different ideas and knowledge, found in various places, into new products and services.

Peripheral Players

Most people would view the nodes on the periphery of a network as not being very important. In fact, Ike and Jane receive very low centrality scores for this network. Since individuals' networks overlap, peripheral nodes are connected to networks that are not currently mapped. Ike and Jane may be contractors or vendors that have their own network outside of the company -- making them very important resources for fresh information not available inside the company!

Applying Social Network Analysis

Software & training in social network analysis are available from our organization. Various applications of SNA & ONA can be found in our social network analysis case studies directory

What is Social Network Analysis?

What is Social Network Analysis?

Social network analysis is based on an assumption of the importance of relationships among interacting units. The social network perspective encompasses theories, models, and applications that are expressed in terms of relational concepts or processes. Along with growing interest and increased use of network analysis has come a consensus about the central principles underlying the network perspective. In addition to the use of relational concepts, we note the following as being important:

• Actors and their actions are viewed as interdependent rather than independent, autonomous units
• Relational ties (linkages) between actors are channels for transfer or "flow" of resources (either material or nonmaterial)
• Network models focusing on individuals view the network structural environment as providing opportunities for or constraints on individual action
• Network models conceptualize structure (social, economic, political, and so forth) as lasting patterns of relations among actors

The unit of analysis in network analysis is not the individual, but an entity consisting of a collection of individuals and the linkages among them. Network methods focus on dyads (two actors and their ties), triads (three actors and their ties), or larger systems (subgroups of individuals, or entire networks.

Wasserman, S. and K. Faust, 1994, Social Network Analysis. Cambridge: Cambridge University Press

from -http://lrs.ed.uiuc.edu/tse-portal/analysis/social-network-analysis/#what is SNA