INFORMS New Social Media Analytics Subdivision Thanks to Dr. Les Servi of Mitre

Dr. Les Servi, who presently works at Mitre, and I go back to our Applied Math student days at Brown University and both of us have continued  to work in operations research and its many exciting applications over the years.

The UMass Amherst INFORMS Student Chapter and I had the pleasure of hosting his talk and visit  in November at the Isenberg School of Management and, as I wrote on this blog, he was terrific! After his presentation, he mentioned that he had proposed, and it was approved by INFORMS, a new subdivision, the INFORMS Social Media Analytics Subdivision, with him as the Founding Chair.

The good news is that this division is now "live" and I received the message below from Dr. Servi to disseminate this good news. Of course, it is not just for students, and more info is in his message, which I am sending out for communications purposes, and since I was asked to.

Best of luck on this exciting new initiative!

INFORMS Student:

After many months of planning today begins a membership drive for a new INFORMS Social Media Analytics Subdivision.  Dues are $6/yr. More information about the subdivision (as well as instructions about joining)  can be found at https://www.informs.org/Community/Social-Media-Analytics/How-to-Join-the-Section.

Please join.

Every now and then there is a singular opportunity to get involved with something new and exciting at its creation and to shape it into something great. I believe becoming a founding member of this INFORMS subdivision is such an opportunity. INFORMS is uniquely positioned to be a central hub for Social Media Analytics as an organization which brings together over 10,000 members who are technical strong, who representing the best in the world in a number of diversity fields, and whose interests range from pursuing pure theory to pursuing the applied, with many doing both.
As a student this is a chance to join early to participate, help guide, and a eventually help lead this new subdivision.  Speaking personally, around 20 years ago I became a founding member of the Telecommunication Subdivision and it was a pleasure to have a front row seat watching it grow from nothing to part of the INFORMS establishment.

After the membership drive I will be organizing a social media analytics cluster of talks for the INFORMS national meeting cf http://meetings2.informs.org/sanfrancisco2014/index.html   There will be well over 2,000 people attending this conference.  People interested in presenting a talk should contact me.

The key to the success of this subdivision is great momentum in its first year.  With many members and a cluster of talks as many and as good as last fall's cluster we will be well on our way.

The new Social Media subdivision seeks to be a unclassified, international forum to bring together
-       Researchers from academia, industry and government to exchange new analytical methods and to discuss newly formed problems;
-       Educators at the graduate and undergraduate level to learn about evolving challenges and solutions being developed and bring them back to the classroom
-       Different domains of application of social media analysis (e.g., from assisting in natural disasters, perceiving of evolving sentiments, to impacting consumption of consumer goods), to identify potential for the cross-fertilization of ideas;
-       Vendors and potential buyers of new tools which analyze social media to encourage innovation;
-       Social media service providers (who might eventually permit the sharing of anonymized data for purposes) and researchers to promote the exploration of new algorithms.
Please join and encourage people in your network to join.

Les Servi
Founding Chair
INFORMS Social Media Analytics Subdivision

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.
 

Great Talks at the Isenberg School of Management

Great speakers provoke and inspire and we can learn so much from them. Students, faculty, staff, and guests from the community benefit immensely from invited speakers plus there is nothing like face to face time in which to exchange stories, share laughter, and, perhaps, even start new friendships.

This week has been an especially busy one at the Isenberg School of Management with many departments hosting speakers including two speakers that were hosted by my department -- Operations & Information Management. The poster above was prepared by the Isenberg School Communications office for a talk that took place last evening and was organized by the Management Department. Dr. Anita M. McGahan of the Rotman School at the University of Toronto spoke on "The Business of Creating Social Value."  She is the President of the Academy of Management, which has 18,000 members. The President of INFORMS, which now has 11,000 members, is also a female, Dr. Anne Robinson of Verizon. Great to see such wonderful leadership at the top of such professional societies!

Dr. McGahan's talk took place at the Integrated Sciences new building and the takeaways were:

1. Work on important problems (think of what you want to leave behind).

2. Create social value through your work.

3. We need new business models -- I liked hearing about innovating in reverse -- rather than having more complicated neonatal incubators use the kangaroo approach (baby on the parent).

4. We should care not just about shareholder value but about sustainable outcomes (rather than organizations).

She spoke about meeting Dr. Paul Farmer, a co-founder of Partners in Health, on a shuttle flight from DC to Boston and also about various new industries and products from wind energy to the Tata Nano car. She is very dynamic and interacted very well with the audience -- I estimated over 400 in attendance, including many undergrads including many students.

Dr. Detmar Straub, A Regent's Professor of the University System of Georgia and the J. Mack Robinson Distinguished Professor of Information Systems at Georgia State University, spoke this afternoon as part of the Dean's Lecture series. His talk was on "Why Top Journals Accept Your Paper." He completed two terms as the Editor-in-Chief of the journal MIS Quarterly. I had the pleasure of joining several of my IS faculty colleagues and one of our doctoral students for lunch with Dr. Straub at the University Club, which is in a building dating to 1728. The food was very good and the conversation fabulous  -- we laughed over so many great stories -- I especially enjoyed his reminiscences about various conferences.

 Dr. Robert Shumsky of Dartmouth was our previous speaker in the Dean's Lecture series. He is well-known in INFORMS and OM circles.

Also, today, the UMass Amherst INFORMS Student Chapter had the pleasure of hosting Professor Michael C. Fu of the Snith School at the University of Maryland College Park. He has degrees from MIT and a PhD from Harvard and he was fabulous. His talk began at 2:00 at the Isenberg School and we ended our conversations at 4:00PM. His talk focused on stochastic methodologies with applications ranging from financial engineering to supply chains. Specifically, he spoke on  stochastic gradient estimation techniques, which are methodologies for deriving computationally efficient estimators used in simulation optimization and sensitivity analysis of complex stochastic systems that require simulation to estimate their performance. His presentation was so clear and I loved such phrases as the "mathematically disadvantaged" and "statistically unconscious."

The photo below I took (apologies that it was not my best) after Professor Fu's presentation. My colleague from engineering, Professor Weibo Gong, also a Harvard PhD and a former doctoral student of Professor Ho's, helped in the hosting.

On November 1, we will be hosting, through the efforts of the UMass Amherst INFORMS Student Chapter, Dr. Les Servi of Mitre, who, coincidentally, had the same PhD advisor at Harvard, Dr. Ho, as did Dr. Fu and Dr. Gong. I have known Les since we overlapped at Brown University. Both Les and Michael are INFORMS Fellows and outstanding scholars. Dr. Servi will be speaking on social media and sports, with a focus on his work in soccer -- it should be a fascinating talk, Last time that he spoke in our series, his topic was on pirates off the coast of Africa! And he gets paid to work on such interesting projects.

Beating the News and the IARPA Project that I Could Have Been Part of -- Data Eye in the Sky

Last week, when I was in Paris, I picked up a copy of The International Herald Tribune only to find an article on a project that I had been asked by a corporation to partner on.

The article, "Government Aims to Build a Data Eye in the Sky," also appeared in The New York Times and, in it, I enjoyed reading the quotes from two of my favorite professional colleagues, Dr. Sandy Pentland of the Media Lab at MIT and Dr. Albert-Laszlo Barabasi of Northeastern University (and renowned in network science). We had hosted both of them in our INFORMS Speaker Series at UMass Amherst and Pentland also was a keynote speaker at our regional INFORMS conference at UMass last May and gave a tutorial at the SBP conference in Maryland last March that I served as the tutorial chair of.

The project is a three-year experiment, and is to begin in April. The title is rather dry -- Open Source Indicators (OSI) program. The RFP was sent out by the Intelligence Advanced Research Projects Activity, which us part of the Office of the Director of National Intelligence and which is the funding agency for this project.

I very much enjoyed the conversations with the researchers in the company that approached me and I found the challenges very intriguing. Essentially, in a nutshell, the goal is to develop a platform by which one can "beat the news" in terms of certain events. The focus, interestingly, was to be on Latin America (all 21 countries, no less).

According to the program overview in the RFP:

Many significant societal events are preceded and/or followed by population-level changes in communication, consumption, and movement. Some of these changes may be indirectly observable from publicly available data, such as web search queries, blogs, micro-blogs, internet traffic, financial markets, traffic webcams, Wikipedia edits, and many others. Published research has found that some of these data sources are individually useful in the early detection of events such as disease outbreaks, political crises, and macroeconomic trends. For example, much has been published on extracting indicators useful in forecasting political unrest from news feeds; public sentiment has been inferred from blogs and microblogs; and disease outbreaks have been detected from web search queries. In addition, Government-funded programs such as the Integrated Crisis Early Warning System (ICEWS), the Political Instability Task Force (PITF), and the Aggregative Contingent Estimation (ACE) Program have focused on methods to forecast pre-defined events. But few methods have been developed for anticipating or detecting unexpected events by fusing publicly available data of multiple types from multiple sources.

OSI aims to fill this gap by developing methods for continuous, automated analysis of publicly available data1 in order to anticipate and/or detect significant societal events, such as political crises, humanitarian crises, mass violence, riots, mass migrations, disease outbreaks, economic instability, resource shortages, and responses to natural disasters. Open Source Indicators (OSI) performers will develop methods that ―beat the news by fusing early indicators of events.

Performers will be evaluated on the basis of warnings that they deliver about real-world events.

After spending time thinking through how I and a student and perhaps colleague could contribute, ultimately, I decided that the time-frame for the preparation of the proposal was too tight, given that it was the beginning of the new academic year and it was not entirely clear to me how big my role was to be. There were regular project deliverables and it seemed that there were some fundamental research questions that one should answer before working on deliverable software.

Imagine my surprise when The New York Times highlighted this project!

It will be interesting to see which organizations/universities/corporations end up with the winning proposals.

The SBP 2011 Tutorial Presentations Are Now Online!

If you missed the three excellent tutorials that were delivered this past Monday, as part of the Social Computing, Behavioral-Cultural Modeling, and Prediction (SBP) 2011 Conference at the University of Maryland College Park, you may access the presentations online!

Tutorial 1: Toolkits for Computational Social Science: Using Honest Signals to Predict and Shape Human Responses

Alex `Sandy' Pentland, MIT

Tutorial Slides: funf Mobile Sensing System

Tutorial Slides: Influence Model

Tutorial 2: Social Network Analysis of Personal and Group Networks

Allen Tien, Medical Decision Logic

Chris McCarty, University of Florida Survey Research Center

Eric C. Jones, University of North Carolina-Greensboro

Tutorial Slides

Tutorial 3: Understanding Social Media: Tools, Applications, and Processes

Nitin Agarwal, University of Arkansas at Little Rock

Tutorial Slides

The above photos were taken at these tutorials.

Thanks again to the outstanding presenters and to the audiences for the great questions and discussions! Also, thanks to the tutorial presenters for making their lecture slides available!