Facebook Data to the Rescue of Metcalfe's Law

The December 2013 issue of IEEE"s Computer magazine has as its theme: Computing Laws Revisited. Our hardcopy issue (my husband is a subscriber) arrived yesterday, on New Year's Eve, and, today, New Year's Day, I sat down to read the article, "Metcalfe's Law after 40 Years of Ethernet," written by none other than Bob Metcalfe, Ethernet's inventor, himself. The Ethernet is the physical transport level of today's Internet. On May 22, 2013, Ethernet industry leaders gathered at the Computer History Museum in California to celebrate its 40th birthday and to catch up on what has become a $100 billion industry (do I now have your attention?).

I have been interested in Metcalfe's Law since, as an Associate Editor of over a dozen journals, and a frequent reviewer of journal articles, as well as a Co-PI on a Future Internet Architecture NSF grant: Network Innovation Through Choice (which I most recently spoke on at the Network Frontiers Workshop at Northwestern University), I not only encounter related controversies but also write and review papers that touch upon this law.

I guess that Metcalfe must have been reading over my shoulder!

Now, back to a controversy: In 2006, Briscoe, Odlyzko (I do like some of his math models a lot), and Tilly published an article, "Metcalfe's Law is Wrong" in the IEEE Spectrum, which you can read online without a subscription. These authors described Metcalfe's Law as both "wrong" and "dangerous."

So, what is Metcalfe's law, you may be asking (for those not so much into hardware). As explained by Metcalfe himself in his very clear and erudite December Computer magazine article: The "law" bearing his name states that the value of a network grows as the square number of users: V= NxN. The law started as a high-concept Ethernet sales tool in the early 1980s and entered into the public discourse in the new millennium when Gilder "championed" Metcalfe's law in his book, "Telecosm: The World After Bandwidth Abundance," published in 2000.

During  a presentation to the 3Com sales force (Metcalfe cofounded this company in 1979), Metcalfe showed the figure below (thanks to his article in Computer magazine) to argue that if  a network is too small its cost exceeds its value, but if a network gets large enough to reach a critical mass, then the sky is the limit.

Valuation of Internet-based companies such as Google, LinkedIn, Facebook, Twitter, Snapchat, and others is clearly important and detractors have said that Metcalfe's law may be overvaluing such firms.

The main critique of Metcalfe's law, noted by Metcalfe, himself, was that Briscoe, Odlyzko, and Tilly countered that not all network connections are of equal value and that the growth in the value of a network is approximately Nxln(N) and not NxN as Metcalfe had stated.

Moreover, neither "law" had been validated empirically until Metcalfe did recently and reported the results in his article in the December issue of the IEEE Computer magazine.

And he used 10 years of real data from Facebook and fitted the data looking at N as a function of time. To estimate the growth of users and individual groups of friends, he first applied a sigmoid function (S-shaped adoption function). He then generalized it to what he calls a "netoid" function using the Python programming language. (It looks as though Metcalfe also thinks in code, which is cool.) He plotted Facebook annual revenue (as the value V) for the last 10 years and used a Python slider to the Metcalfe's function to "get a pretty good visual fit to this data" as he displayed in the figure below reported in Computer magazine.

Metcalfe also notes that a more elaborate model of network growth and value would involve using "nesting netoids." Fascinatingly, he observed that Facebook groups seem to be netoiding (a new verb) towards Dunbar's number, which is due to the anthropologist Robin Dunbar who theorized that humans have a cognitive limit on the number of people with whom they can maintain stable social relationships with this figure being about 150. And, since Facebook has about 1.06 billion users and 150 billion friend connections this implies  an average of 141 friends per user.

So, as we begin to celebrate the New 2014 Year, it is quite interesting that we are also marking technological advances that challenge and intrigue us in both theory and practice and that are still very much with us such as the Ethernet, which is now 40 years old!

There is also a great interview with Bob Metcalfe, thanks to Charles Severance of Computer magazine, which can be viewed below.

A Brilliant Talk on Social Media Analytics + Sports by Dr. Les Servi of Mitre

Yesterday, at the Isenberg School of Management, we had the distinct pleasure of hosting Dr. Les Servi of MITRE, who is an INFORMS Fellow (and whom I have known since our days at Brown University as undergraduate students). Dr. Servi delivered a brilliant talk on his latest research on the topic: Analyzing Social Media Data Having Discontinuous Underlying Dynamics.

Dr. Servi's presentation was part of the UMass Amherst INFORMS Speakers Series, which the Student Chapter helps me to organize and to host.

His talk was on his paper in Operations Research Letters, just hot off the press, and published in the November issue.

The paper begins with the statement, which immediately captures your interest (as did his talk): Although physical objects follow well understood Newtonian physics and are free of discontinuous dynamics, emotional intensity dynamics evolve continuously with unknown dynamics until a tipping point or external event triggers a discontinuity. 

In his presentation, Dr. Servi asked whether anger has dynamics (the same about sadness and positive emotions). Is there a formula that can capture the anger of citizens and is there a  momentum associated with anger? He concluded that sadness (and other emotions) follow dynamics that are different from those of rockets since there are discontinuities. His paper not only presents a model for a more nuanced dynamic for emotions but also a dynamic programming  algorithm to solve the associated optimization problem that identifies times of emotional discontinuities. He then illustrated the new method for the  analysis of mood shifts reflected in 380,000 Twitter messages related to one of the world’s most popular soccer teams, Manchester United, during their 2011–12 season.  He was impressed that so many in the audience at the Isenberg School knew of this team and its sport (a finance audience at a talk he gave in Boston did not recognize the team).

And what Dr. Servi discovered through analyzing the data was fascinating and not what one would expect immediately. The figure below displays the Mood Shift Analysis of the Twitter messages showing a breakpoint on 2/6/2012 and 5/14/2012.

The discontinuities in mood associated with certain dates were not due to wins or losses of one of the world's most popular sport franchises (and one student in the audience had been to Manchester games) but one marked the anniversary of the following event: the tipping point found on February 6, 2012, might be due, according to Dr. Servi,  to it being the 54th anniversary of an airplane crash in Munich which killed 8 Manchester United players and 3 staff and injured 9 other players as well as the team manager. Among serious Manchester United fans this event and date are well known despite it happening so long ago.

 

With a great talk such as this, our minds just percolated with ideas and questions. I asked whether MITRE had applied for a patent since the possible applications from finance to politics were simply stunning and the answer was ,"Yes," --  see here.   One of my colleagues, Dr. Ryan Wright,  asked a question about acceleration, which I thought was really interesting -- for example, could the model and algorithm track herding/crowding behavior? Dr. Rod Warnick of our great Hospitality and Tourism Management Department also asked a great question about seasonality with reference to Google as did several of the students. My colleague, Dr. Senay Solak, continued the conversations.


The discussions lasted as time just flew by until close to 4 o'clock and I think the students from the Isenberg School and the College of Engineering that came as well as the faculty will never forget this talk. We thank Dr. Les Servi for the clarity and brilliance of his talk! The previous time that Dr. Servi spoke in our series was in the Fall of 2006 when he talked about tracking pirates (and that was even before such activities hit the news).

 

Special thanks also to Dr. Bruce Weinberg, the Chair of the Marketing Department at the Isenberg School, and a social media star,  and to Dr. Weibo Gong of the Department of Electrical and Computer Engineering at UMass Amherst, whose PhD advisor at Harvard University was Professor Larry Ho (also Servi's advisor), who joined Dr. Servi and me for lunch at the University Club.

After lunch, Dr. Servi and many others joined us in a celebration of the  3 awards that we received at the INFORMS conference in Minneapolis. The cake was delicious and the company simply wonderful with even Dr. Amir Masoumi joining us from Manhattan College.

 

What a great time to be an Operations Researcher living in an era with a proliferation of data. What information will the data reveal and what new discoveries?! And as Dr. Les Servi said, Philip Morse, a pioneer of Operations Research, would be very pleased.
 

New Female Amherst College President Tweets

Lately, there have been articles on leaders, including the CEO, Rupert Murdoch, who are now tweeting and how their personas, and, perhaps, leadership styles, are coming through. The New York Times had such a column on Murdoch yesterday.

Now, the Chronicle of Higher Education (CHE) has an article on the new President of Amherst College, Dr. "Biddy" Martin, who took over the Presidency from Anthony "Tony" Marx this past Fall (he is now head of the New York Public Library).

The article begins in a wonderful way, speaking about Amherst, the town that I live in, as being idyllic.

It also discusses the challenges that Dr. Martin faced in her former leadership position at the University of Wisconsin and asks why she left there to assume the Presidency of a small, outstanding liberal arts college (that actually is more diverse than many institutions).

The CHE article also has some inside information that I was not aware of -- of how Amherst College is essentially run by a "Committee of Six" with weekly 3 hour Monday meetings.

It quotes Dr. Martin as saying: "Everyone warned me about it," she says of the power of Amherst's faculty. "Someone just recently told me that a former president of Dartmouth is alleged to have said: 'Being president at Williams is a fun job. Being president at Dartmouth is a hard job. And being president of Amherst is an impossible job.' There's a reputation of faculty being ­really hard on presidents."

It also notes the anti-professionalism credo at this liberal arts college (and I can personally attest to this since I have had Amherst College students in my office trying to figure out how they can take courses at the Isenberg School of Management and the College of Engineering with the Amherst College restrictions). Yes, we are part of the Five College system but that does not mean that students from Amherst College (as I have found out) can take any course that they are interested in at UMass Amherst.

I do wish Dr. "Biddy" Martin all the best in her new leadership role. I think that she will be outstanding. Students are starting to notice already.

You can follow President Martin on Twitter.

The article from the Chronicle of Higher Education.

Social Networking through Blogs, LinkedIn, Facebook, Twitter, and Beyond

The INFORMS Annual Meeting begins soon in Austin, Texas and I am so looking forward to reconnecting with former students and seeing colleagues from around the globe! I am also very much looking forward to giving presentations, listening to the latest research, taking part in several business meetings and award ceremonies, and to simply enjoying the various social and special professional events.

The conference will begin, for me, next Sunday morning when I take part in a panel on Social Networking and Operations Research that was organized by my fellow blogger and very dynamic colleague, Professor Laura McLay of the Virginia Commonwealth University, as part of a cluster of panels organized by the super-blogger and promoter of Operations Research, Professor Mike Trick of Carnegie Mellon University! Joining me on the panel will be Professor Wayne Winston of Indiana University and Professor Aurelie Thiele of Lehigh University.

We will share our experiences with social networking tools from blogs to Facebook and Twitter with Q&A from the audience, led by Professor McLay. I am certain that the discussions will be very interesting and illuminating, so join us, if you can!

Professor Trick has promised to cover the panel discussions on his blog and to tweet about them as well

Hope to see many of you at INFORMS in Texas next week where the weather is much milder than in Amherst, Massachusetts!