What variables are more important in the determination or change of friendship in different stages, grades, gender, interest, or similar economic background or experience? What self-identity cognition would be reflected from it?

what constitute a tie? direction, same-sex, other-sex, specific subgroups, strength(very subjective to define the strength of a friendship).

This is a great example of Kohonen's Self-organizing Maps and the use of the U-Matrix. The authors were very thorough in explaining how it can be used.

Data Structure

I really like this concept and application of SNA with integration of critical discourse analysis (CDA), which is a course I am taking in the fall!! In another class, we read about critical quantitative approach, and I now think what makes it truly critical might be the integration of a mixed method approach, where something like ethnographic case studies or in this case discourse analysis is used in combination with SNA/statistical analyses to give it more robust findings.

This paradigm shift may be supported by a similar shift from individualized learning theories to socio-cultural theorning theories too.

a huge limitation to the application of SNA in general, in my opinion. while it's fascinating to look at particular networks and see some other structures in some of the studies i was reading to better understand my own issues, the findings weren't something i would be comfortable applying to my situation. people are so unique and add a social network of other individuals on top of that, plus environment, plus any number of other factors and it feels very limiting.

yeah, this wasn't so useful for an interconnected network of over 400 individuals.....

Since no one had "done" what I was looking to do I also found it helpful to look for studies that had the same general goal as mine. Even if we were talking about departments in a huge corporation or different professional development groups and how they shared knowledge it was pretty easy to find things in common with my own information.

I would be interested in trying this especially because this textbook provides some good step-by-step examples using this package.

I would love to see more of these - in published papers, for example - or just tutorials that take us from raw data to tidy data to analysis/computations in R.

I hope to use survey design as a component of my data collection for a future project.

This is certainly applicable to my own study. My original thought was that my data could be undirected, but I'm now questioning that. For example, it would be interesting to see if an initial contact between two students was then reciprocated, or if there were other contacts that seemed to follow from the initial.

This makes a connection to my prior knowledge about traditional statistics, binary Logistic regression(dependent variable is binary, 0 or 1) and multiple Logistic regression(dependent variable has multiple levels, just like the school leader network example, four possible outcomes).

This is (unfortunately) reminding me that I need to finish my stats exam due later this week and try to come to some conclusions like this after spending probably the next 8 hours staring at awesome output in R... but I digress... yes, this seems like it would be very applicable to my study. :)

I have a background in quantitative statistics. The use of a t-test assumes normality of data. I know that normality does not matter for SNA, but is this particular section referring to a nonparametric test that works like a t-test or is it actually referring to the use of a t-test and just ignoring the assumption of normality?

Ok... So now this is making a little more sense for my own data. In my case, I could analyze the countries geographic loaction as an attribute varibale that predicts the probability of certain industries having multiple companies in a given country. Does this make sense?

Ahhhh... This makes sense. I asked about this in the previous chapter.

Ooh! This seems like it would be very useful for my divvided up SP and CP, which I have categorized at L, M, and H as well. So, "Do students' ties vary by their level of SP?" would be the question I would ask.

Oy. This (multiple linear regression) is much harder for me to wrap my brain around, but I'm going to give it a go (especially since I have so many variables and it might be useful for tying them together). Again, I have SP, CP, and discussion forum type. If I did the surveys, I'd also have perceived sense of belonging. How well does a student's perceived sense of belonging predict his/her level of CP in discussion posts, controlling for discussion forum type (for example, only looking at large group discussions)? That doesn't get the SP in there though, and may not actually be a great model of regression. :/ Help?

This is very similar to what my research is doing, where engagement is defined as SP and academic achievement as CP. :)

Again, if I were to try to apply this (p) to my own data, I could look at things like gender, race, etc, but it would make more sense to see if SP was tied in--in other words, take the same scenario from p1 (if a student respond to another (say, in a large group discussion), is that student more likely to respond back when higher levels of SP are involved? I think* I applied that correctly.

Again, attempting to apply to my own study. This one (p1)seems straightforward. If one student responds to another (in a large group discussion), is the other student more likely to reciprocate by responding to that student in future discussions?

I have next to no stats knowledge, so I'm going to try to extrapolate this out in regards to my own research to try to better understand it (hopefully!). In using my own research with SP (social presence) and CP (cognitive presence). I'm going to start with the varibles: levels of SP, levels of CP, discussion forum type. A question I have been asking is whether discussion forum type affects SP and/or CP. Modeling the question the same way as this one, it might be whether students are more likely to show higher CP with students they were in a programmatic small group discussion with versus just large group. I think this models this line of questioning, at least. This probably doesn't get the SNA part in. So, trying again... Are students more likely to respond to a student in a large group discussion that they formed a connection with in a programmatic small group discussion or a random small group discussion? This doesn't get the SP or CP working in there, but it gets the SNA. So part of what I'm studying. But, since I'm graphing SP as a weighted measure for SNA, maybe it could be whether students are more likely to demonstrate higher SP in an ensuing large-group discussion with students they were in small programmatic group discussion with in a previous module. Does that get all the parts working approporiately in a MR-QAP-procedure question??

this is something i've been struggling with this entire course. in particular, for my network, one or two members who are always participating and holding these networks together could very easily get a new job, move onto a new opportunity etc. how to keep the networks so intertwined that one or two people leaving wouldn't make the whole thing fall apart is what interests me.

Would running such tests require a need for assessing latent variables that emerge from network analysis? I will keep reading, but from what I know of SNA, it seems like you are only analyzing observable variables and it would be difficult to obtain a correlation from such unique variables. Am I way off here?

I have been dealing with this issue all semester. I am really struggling to determine which questions are appropriate and which can be answered using SNA techniques. Perhaps this is due to the type of data I am working with, but I am still working on developing sound research questions.

Since my own study takes these measures weekly, I'm curious to see how the statistical aspect may help draw connections between weeks and predict what could happen in future weeks.

Although, I will say I think this is only true in a broad sense. For example, I think I may be able to predict from a couple weeks of SNA data who the central players in future weeks will be (rock star students tend to retain that status throughout), but it may not be able to predict who responds to whom. Though such a measure may not be all that useful anyway.

Coming back to this after reading the chapter, I'm having a difficult time deciding whether statistical approaches make sense for me. I am trying to make generalizations, but it's not around categories (like gender, race, etc.). Unless maybe my category is SP (social presence)? To make a prediction about students with high SP having high CP (cognitive presence)?

If your network differs from a typical random creation, then you can perhaps make a claim about unique properties.

For my own study, this would be making a claim about the connection of SP to CP in certain discussion forum types to suggest that you can get the biggest bang for your SP and CP buck by adopting a certain discussion forum type.

In terms of my project (looking at racial and gender-based biases in communication between undergarduate students in an online class), then I could use this same rationale and process in order to make generalizations to a broader population?

In my case, ego-centric networks are particularly interesting. I am looking forward to see how different individuals from first language groups interact with learners from other first language groups. Also, how does this correlate to their English proficiency, grades etc.

Since my groups are small with four to six participants, a one-step neighborhood probably makes most sense, but if I were to look at an egocentric analysis with the moderator as the ego, the larger or complete network would be more applicable?

I would prefer to define the "neighborhood" for my ego-centric analysis to one-step, because I am most interested in who that person is directly connected to, instead of looking at the larger network that the ego is nearly connected to.

If I were to apply ego-centric networks to my project, I would focus in on studying members of the game development community that have gone through a public education program to see if they have become more well-connected in the community since going through the program.

Comparing different groups with the same or similar structure? Or differing patterns of interaction within the groups? Or both?

When looking at my data set, I'm most curious to analyze the ego networks of particular students that either do not feel connected to the school or regularly struggle to academically achieve. Perhaps individual interventions can be designed to aid the educational experience of these students.

The term 'advantage' seems to be used loosely. I understand the power that A may be able to exert over students B & C, but given the various values of weak/strong ties and dense/disperse networks, I do not totally see how the term 'advantage' always applies in this scenario.

This is the most succinct description of the value of strong and weak ties I have heard yet.

A similar theoretical foundation may apply to 'echo chambers' noted recently throughout social media.

This whole concept is a huge part of what I want to get out of my data set! This is exciting and also terrifying because I will have to figure out how to actually get these measurements....

I am going to see if it makes sense to do something like this with my data in terms of OIT v. non-OIT or instructional designers v. other types of employees. So many potential ideas!!!

I had not thought of that until they spelled this out. that actually makes a lot of sense.

Thinking about direction makes sense for my study. It could be interesting to compare an ego-centric network to look at one student (Student A) to see if Student A's out and in neighborhoods are the same or mostly overlap. From what I've seen in my data so far, this has only been the case when students are placed into small groups. When it's the discussion forum as a full class, there is significantly less overlap.

It could be interesting to compare students' sense of belonging/community on the basis of whether they have a strong in or out neighborhood. I could see students who have high out but low in as feeling disconnected, and students with high in but low out maybe not even paying attention/not really caring about sense of belonging. Methinks I need to add a survey to my research...

This may or may not make sense for my research. Since my network is small (19 students; 20 if you count me, the instructor), it's easy enough to look at the whole network (socio-centric) and then decide if it makes sense to zero in on particular students. Reasons I may want to use ego-centric: To study high-performing (vs low-performing) students' networks; to isolate students showing high cognitive presence (one of the aspects I'm researching) to see what their individual networks look like; to explore students with high social presence to see what their networks look like--does quality of SP go along with quantity of SP?

If I were administering surveys (which I do not believe I'll have time to do), then I might want to look at egos based on survey results, for example, to a ask like "Do you feel a sense of belonging in this online class?" to study how students' perceptions of belonging align with their actual quantity and quality of ties.

The data presented in these tables is often kind of confusing, if it is generated from the program they are using.

Is it common to perform both types of analyses on a dataset?

I think we calculated closeness centrality of vertices (and also the closeness centralization of complete network) two week s ago, it used the similar computation method as this egocentric network closeness centrality. It seems like that when calculate closeness and betweenness, you have to include indirect connections of a given ego, not just direct connections in the egocentric network.

I can see some application of tie strength both in my project for this course (analyzing the effects of gender and race on interaction between actors) and beyond my dissertation research: how do technology integration processes disseminate through a network of teachers?

Seems similar to a caution when using Case Study qualitative research methods - it's best to use caution when generalizing from case study research.

This reminds me of strong ties theory and weak ties theory(also called structure hole) we had read before which are competitive theories , but both theories can explain some certain social phenomenon. Strong ties theory can explain how strong ties affect people's behavior or attitudes etc., and weak ties play a role of bridge to disseminate (non-redundant) information. So I think what matters is your research question/interest, your research question will drive you to apply appropriate theory and interpretation.

This is useful. Sometimes I wish different studies would just show us the surveys they used so I can get a clear idea of types of questions and what is visualized.

This is important for my own understanding of the "Why" of SNA. It made sense to disengage the social portion of the practice and focus on the composition of the ties. An ah-ha.

I'm not sure what theory I should be leveraging to make cut-offs in my analysis of Slack interactions.

It may be interesting to apply this after I've had students in the same small groups for a couple weeks for their discussions and then return to a whole-class discussion (to see if the students respond more so to the students they had been in a group with previously).

I could see this being useful for looking at my own research. Not many of the students are interacting beyond the minimum requirements for responses (typically, 2), so I could use this to separate out those who are a bit more easily (so doing a 3K-core).

Moving forward into post-dissertation work, I can see how the idea of equivalence might apply in looking at technology integration processes across schools. But, for my research questions posed in this class, this isn't very useful.

This one was easy! Getting good a good directed network to play around with it with into R and able to be modified was... way harder than getting this info.

reciprocity(g, ignore.loops = TRUE)

There is an additional mode operator where if you put the mode = ("ratio") it calculates (unordered) vertex pairs are classified into three groups: (1) not-connected, (2) non-reciprocaly connected, (3) reciprocally connected. The result is the size of group (3), divided by the sum of group sizes (2)+(3).

This reminds me of 7 degrees of Kevin Bacon or using Facebook to find how connected you are to a complete stranger.

Step 1.

Centralization interests me for analyzing discussion forums--are there key players, and do these key players show higher degrees of cognitive presence?

Calculating for centralization by number of connections seems quite straightforward in R: centralization.degree

For examining either my original project idea or my new one, I think this will be a useful equation. For example, in my current project idea, it would be interesting to see the density of a given network where I have limited them to two responses total within a given assignment.

I am very interested in clustering measures, because I plan to analyze data from a Slack group that I am a part of, where I suspect there are many subgroups who only interact with each other.

After looking around for some different clustering algorithms, I found the "cluster_label_prop" function in the igraph package, which seems to do what I would like to do. To summarize, this function automatically detects groups within a network by initially labeling every node with a unique label and at every step each node adopts the label that most of its neighbors currently have. In this iterative process densely connected groups of nodes form a consensus on a unique label to form communities.

There seem to be many different ways to define clustering though, so I am sure that I will need to do more research on the topic of clustering as I move forward with my research project.

This video was a great and simple explanation for calculating Betweenness centrality. It will be interesting to look at this in my data set (eventually).

Are we allowed to include nodes for John and Holly if they are identified by others, but without using their name? For example, we would refer to John as Anonymous 1 and Holly as Anonymous 2. Or would we have to exclude any data that involves them, regardless of anonymity?

This seems similar to conducting a program evaluation. I guess the only difference would be the application of network analysis.

I think this is a really good example of SNA research. It would take a lot of thinking to operationally define bullying as identified on facebook, but I bet the results would be interesting. I wonder if something of this nature has already been studied.

This is the hard part! Who/what participants at the University represent range from "college" to "department" to "faculty groups" to "student union" to "tight knit group of people who happen to teach online courses". how to collapse them is hard to quantify, even if you know who they are and how they're related to various things.

this is my problem. most of my ability to collect data relies on this (i.e. I know who attended an event) but the event attendees are the people I don't need to reach or concentrate on. They already attended! How to study the real social networks of people who are interested or invested in an event but can't/won't/don't attend is what I need.

If planning to use SNA within a case study, it's important to know if you're a Yin, Stake, or Merriam-oriented case study person.

It is common to use students' family income or parents' education to predict students' academic performances. Educational researchers also usually talked about culture capital and social capital, but I think It could be more interesting employing SNA method to explore what resources certain student can access except from parents and how those resources impact students' achievements. In addition, I think we need more research investigating the extent to which social capital is independent from socioeconomic status.

Your summary of this area was very helpful Bodong! Your visuals were very useful to understand the structure of data necessary for SNA.

Now this helps me to understand the stroke patients case, stroke people who go to hospital early have weak ties with other people, maybe because the other actors in the stroke people's networks are more likely to have resources (knowledge or experience refer to stroke symptom) which stroke people's family members don't have.

This is such an interesting question! My area is in college students, so I don't have to worry so much about parental involvement, but for those in K-12, the assumption that this sort of close communication is good. I wonder if it's like the stroke victims where having more weak ties among the network is a good thing. Though I can't fathom why that would be the case in this situation.

This would relate to the talk we watched on stroke victims. In that, there was more constraint because of how close-knit the stroke victims who came in late were to their networks (presumably, families). If I understand it correctly, there would be few bridges in these networks because the nodes are already connected to each other, so there's not a "bridge" to a non-centralized group.

Is it possible to indicate other types of relationships between actors, other than a 0/1? Or do you just need multiple tables identifying different relationships between the different actors?

Very useful visualization of what data looks like.

This is an application of SNA that I haven't considered before; when I think of SNA I generally think of network graphs. Though this is definitely an interesting application of SNA data.

The social factors are at least as important as the individual attributes when studying a human phenomenon.

I could apply ego graphing to mentor networks. I could establish an ego network for each mentor and compare them for interaction and relationship to student interest and motivation.

Applied quantitative SNA methodology

Is there a tool to model SNA over time? In other words, while the graphic snapshot these graphs represent is useful, I think being able to see change over time would be a yet more powerful tool.

An interesting relationship for my research is L1 (first language). Most EL students drift towards students that share their L1 and a similar cultural heritage. However, it is always interesting to see Somali students in class using commands in Spanish during class!

Great example of SNA at work.

I am very interested in studying the diffusion of knowledge from mentors to mentees as well as between peers in an astronomy related forum

Interesting analysis: The triangulation of trust, relations among teachers and the relationship between social capital and student outcomes.

This seems exciting and full of possibility. I'm curious what the proliferation of this type of research will do to SNA of small communities, such as individual classrooms. I imagine studying both scales can be very beneficial. I hope both continue to grown in their influence and research stature.

Once I get more resources together, I have a website, 26ers.com, that I would love to attach to an SNA like this. The site is aimed at helping emerging readers explore literacies (traditional text, video, and graphic) through a mobile device and connecting that practice to their lived experiences.

do the tools exist to model the dynamics of these relations in real time? i think it would be very powerful to show how these relationships change over time, as well as linking what the real-world implications would be.

I would love to see how SNA and peer influence affect second language acquisition. I can see how this might help districts/schools support learners upon arrival. Connecting them to important social structures to support learning.

I think background characteristics or students' attributes also affect how friendship networks form. Like attracts like, students with some attributes in common are more likely to form a friendship network, so I think attributes also play a critical role in this case. But I also agree it is a good way to tell a story from the social network perspective.

This reminds me a course" the introduction of sociology", in that course, the instructor talked much about social relations embedding economy. He used Facebook (maturing cybernetworks) as an example to illustrate how Facebook uses social network to make money, it employs user data especially the friend relations to advertise and sell products to certain users. And a lot of vivid examples related to economic activities were presenting, such as how Chinese people or Jewish people use culture networks to conduct transactions abroad.

By "defy," does McFarland mean to misbehave? If it's also about not completing work, I wonder how this same scenario would play out in the online realm.

I hadn't really thought of SNA in these terms, though it does make sense. This reminds me of our current political situation. I wonder what work SNA has done to analyze this. I'm sure I could find some things, but if anyone's run across something they'd like to share, I know I'd be interested.

I think this is essential for teachers to understand when dealing with behavior, it is social. Many of my colleagues realize this, and deal with behavior by looking at who students interact with, but it seems like there is much more that could be done in this area.

I find this to be an interesting example because it draws ties to behavioural science, education, child development, psychology and SNA in a clear illustration of how SNA may be used to analyze adolescent behaviour in a school setting.

Diffusion--as I understand it--is tracking how a particular phenomenon moves through a social network. This reminds me of a TEDTalk on how to start a movement: https://www.youtube.com/watch?v=RXMnDG3QzxE

This makes an interesting point, one which is important to keep in mind when analyzing a network--you know only the bounds of that particular network and thus any hypothesized implications of, for example, peripheral members can only take you so far. Being able to fully analyze would mean access to information from other classes (in the context of education) and beyond. This already got more complex...

Suppose a de-tracked class at a racially integrated high school has a large variation in school performance (perhaps measured through GPA) within the class. I'd be curious to analyze the friendship nominations therein. I'm not quiet sure what question to ask, but I'd hope to better understand what barriers and bridges facilitate inter/intra-racial friendships in this scenario. The same question could be asked about gender, class, language, ect.

As I read more about SNA, I continue to realize just how new this terrain is for me. There seems to be a lot of potential to study and learn interesting things. As of yet, I barely know enough about the tools within this methodology to even ask an appropriate question... haha!

I had never considered this to be a type of "social network" or to be measurable in terms of the strength of ties between organizations.

Can't help but think of the division of tasks within my own household. I find it interesting that stronger ties suggest more segregation between husband and wife. Maybe the thought is that when there are less strong ties in the family structure, they rely on each other more and hence work together more?

What's an example of this type of "chain" network? I see the logic in the argument, but am having difficulty seeing its application.

How might this show the ways in which teachers view their students? How might social environments in and around schools lead to teachers viewing their students with a deficit-thinking mindset? Or with an attribute-thinking mindset?

What about the speed at which networks can now develop and morph? Is there a tool developed that we can use to analyze speed of network development, its efficacy in achieving its purpose (whatever that may be) and triangulating it with findings in network research done from a physical science point of view and the social science analysis? ...this is clumsily stated, actually.

Probably critical to understand social factors from a cultural viewpoint, also. As online classes cross political boundaries, Cultures may have differing expectation that 21st century users may or may not understand about each other and that may or may not impact student persistence...Is this a fair observation?

Interesting - connections among students contribute to their willingness to persist in online course. Social capital and personal motivation are also mentioned. Would love to read the final reports.