A DEMONSTRATION OF THE SOCIAL MEDIA TRACKING AND ANALYSIS SYSTEM (SMTAS): THE HURRICANE SANDY BETA TEST

Feb 5, 2013

GHP Conference Room, Building 1, 12th Floor 

PRESENTED BY:  Arthur G. Cosby, William L. Giles Distinguished Professor and Director, Social Science Research Center, Mississippi State University

Starting in the summer of 2011, a group of scientists, research associates, and graduate students at the Social Science Research Center began to develop a suite of software applications that were intended to create a capacity to track and analyze a wide array of social media platforms.  The goal was to have a system that would assist researchers in using social media as a source of scientific data for exploration and investigation.  The result of this endeavor was the Social Media Tracking and Analysis System (SMTAS).  The system became fully operational in the fall of 2012 and was beta tested with Super Storm Sandy.  The system proved to be highly effective and resulted in a significant gain in our understanding of the role and implication of social media in natural disaster events.  We now have an appreciation of the volume of social media communications and their resilience in the face of storm events and power failures.  We understand how social media was used as a recovery mechanism, especially in the formation of “organic responses” to the storm event.  We also were able to track public sentiment concerning major relief agencies and political leaders in the impacted areas.  Interestingly, we have collected over 4.5 million tweets and an estimated 400,000 images of the storm and its aftermath.  Additional analysis is addressing a myriad of other researchable questions.  

SMTAS is organized in a series of modules that provide unparalleled capacity for research applications with social media.  Our access module enables researchers to utilize over 20 different social media platforms, such as Twitter and Facebook.  For example, we have access to the full firehose of over 400 million tweets (worldwide).  Our tracking/scheduling module will allow the researcher to track social media in terms of 1) word-choice (phrases), 2) location, 3) klout scores, 4) complex time designs, 5) volume of tweets, 6) and other features included in social media data.  In terms of research design, the system has the capacity for primary, secondary, panel, and specialized tracking. 

The SMTAS data module is constructed to handle the simultaneous acquisition and processing of an unlimited number of studies.  It is a web-based system that allows data file collaboration among researchers.  It also has access, where available, to archived historical social media.  Coding and classification capabilities include an option for human cross-validation.  The analytics module includes frequency and trend analysis, a geographic interface with Google Maps, word cloud features, klout analysis, event analysis, and sentiment analysis.  Databases can also be downloaded from the system for further analysis using statistical software and other analytic products.