I just returned from Durham, North Carolina where I was at the Harambee 2010 Social Networks for Educators workshop.* I was there wearing two hats: 1) as someone who is qualified to talk about teaching a social networks course (using this text) and  2) as a teacher interested in using social networks to get high school students interested in social networks.** There were about 40 other academics there interested in using social networks in education, from all sorts of disciplines: computer science, communications, sociology, and education mostly.  The goal of the conference was to assist educators in 1) developing new courses using social networks, 2) finding ways to implement social networks into existing courses and 3) help students develop better critical thinking skills.

I came into the conference with the following thought: the teaching of social networks can be divided into a simplex like below, where a class is somewhere along the boundary.  This leads to classes which are a combination of sociology, mathematics and engineering.  The study of social networks is a discipline in itself and each field has its own approach.

In retrospect, I was thinking too narrowly.  Rather than being a discipline in itself, social networks are a great pedagogical tool to reach some other learning goal. For example, for students early in their CS education, social networks make a great introduction to algorithmic and game theoretic thinking. For sociology students, social networks are a great introduction into statistical analysis and complex systems.  Rather than teaching social networks as an end in itself, there are much broader goals that can be accomplished.  This is definitely a skill I can take into a K-12 classroom in the fall; I conjecture that high school students certainly know about social networks (i.e. Facebook) and are vaguely familiar with the concept of network.  This can be leveraged with good examples to help students develop critical thinking skills: many things can be modeled as networks: economies, ecologies, supply chains, etc.  Recognizing networks is a skill that every person in our modern society should have, they’re so pervasive.

A couple random highlights of the conference:

Ben Shneiderman’s inspirational talk about how the future of CS is modeling computational AND human behavior.  His NodeXL project is really impressive and would work great for an introductory networks class.

Jon Kleinberg‘s keynote talk at the end of the conference.  He concisely summarized what I was trying to say the day before, when I spoke about teaching a course using his book.  It was nice to hear another CS theorist talk at the conference, I felt a little lonely in CS theory-land at times.

That summarizes my Harambee adventure this year. Hopefully, next year, I’ll get invited back to talk about my experience using social networks to encourage high school students.

* – The conference was sponsored by the NSF CNS-0722288. Thanks NSF!

** – I am a NSF GK-12 Fellow, so I will be spending my fall in the classroom with a teacher! Thanks again NSF!

One of my colleagues in my lab here sent me a link to this paper, by Sitaram Asur and Bernardo Huberman at HP – Predicting the Future with Social Media (PDF). I’m not sure if this was published in any conference proceeding or a journal. Either way, their findings are really cool.

They take data collected from the Twitter Search API and extract data about 24 big Hollywood films — i.e. how many times people talk about the movie, post a link to the film’s website, etc.  Then, they take this data and compare it to data from the Hollywood Exchange and the box office returns.  They show that Twitter chatter is a tremendously accurate predictor (R^2>.90) for the box office returns. Even better, they show that for the films they selected it is a better predictor than the Hollywood Exchange.  They expand on their findings by considering the “sentiment” of the tweets and show that this is also a significant indicator of week 2 movie success. The twitter chatter is a good analog to traditional word-of-mouth marketing.

This is the first quantitative finding that I’ve seen that shows a social network is a good indicator of some product’s success. There are lots of business books out there claiming that viral and social marketing is going to revolutionize the world.  The general interpretation seems to be: if we plaster our product all over social networks than this automatically equates to higher profit. The above findings show that this is generally not always the case; social networks are more of a conduit for traditional word-of-mouth advertising. Simply just plastering social networks with your promotional material does not appear to be a good predictor of your early performance.  Furthermore, if people think your product sucks, negative sentiment among the social network users does translate to poor performance later on.   So, I guess it still pays to make a good product, rather than unnecessarily spending money advertising your promotional material on social networks.

Yesterday, I finished my semester project for my randomized algorithms course.  I started the project almost a month in advance since I knew there was going to be a significant amount of research and reading to do. The original plan was to create a mathematica module for processing Exponential Random Graph simulations.  The concept is this:

You have some observed social network, collected from data or in the field.  You want to know things about the relationships of people in the network, like, how likely are people to form connections randomly or do they form connections based on other sociological things. For example, if Alice is connected to both Bob and Eve, is there likely going to be a relationship between Bob and Eve? In other words, do they complete the triangle?  Standard random graph models can’t test for this but we can use exponential random graphs. The output of the algorithm is a set of values that indicate how strong various network structures are.

My presentation went alright. In the mathematical sciences (engineering, math, etc) proofs are the only method you can use to show something is true. In the applied sciences (communications, sociology, statistics) the only method you can use to prove something is statistical inference. So, explaining inference to engineers is difficult since they don’t encounter it (I think they should!). Explaining math to social scientists is challenging since they’re not familiar with proof techniques (what is the contrapositive again?)

I haven’t finished the paper yet (almost done) and I will post the results here shortly. In the mean time, I’ve compiled some of my thoughts about approaching this topic in the future. This is what I want to study (using computer science theory in other fields) so I am noting this for posterity.

• Use more visualizations to explain inference.  Mathematicians love proofs and it is ok to use math on your slides. However, when talking about statistical inference, you’re looking at how something observed fits something hypothesized.  The best way to do this, I suspect, is to plaster a N(0,1) curve on the slides and point to where things fit.
• For social networks stuff, use examples! I used a couple examples in my slides and people found it helpful and interesting.  There are so many great visualization tools for social networks, so I should use them more.
• Take a course on econometrics.  I’m doing this next year.  Econometrics is using statistical inference to reach economic conclusions. There has to be some good techniques they use.
• Write the slides AFTER you write the paper. In this case, I was so worried about the presentation, I did it before I wrote the paper and ended up rushing the paper.  Next time, I’ll flip it and spend time worrying more about visualizations and teaching people than plastering equations on slides.