Modeling Recurring Event-Driven Dynamic Group & Subgroup Formation on Social Media.

About Sandia National Labs

The Sandia National Laboratories (SNL), managed and operated by the National Technology and Engineering Solutions of Sandia, is one of three National Nuclear Security Administration research and development laboratories. SNL is located at the Kirtland Airforce base in Albuquerque New Mexico.

For more than 60 years, Sandia has delivered essential science and technology to resolve the nation’s most challenging security issues. A strong science, technology, and engineering foundation enables Sandia’s mission through a capable research staff working at the forefront of innovation, collaborative research with universities and companies, and discretionary research projects with significant potential impact.

About Our Grant:

The technical work is combining social networking analysis with information systems analysis, text mining analytics, and conceptual blending analysis to model: (a) the subgroups that form based on recurring events on social media; (b) the information shared between subgroups; (c) the cognitive residue of this information sharing; and (d) how this cognitive residue affects the formation of future groups and subgroups. Twitter is the social media platform being used, and the recurring events studied include television shows, celebrities, and presidential tweets. This work differs from traditional social network analysis (SNA) applied to social media, which is content agnostic and focuses mainly on actors and direction of communication.  While appropriate for categorizing groups, ignoring content — both communicative and cognitive — limits SNA’s ability to explain why groups form and how groups evolve over time, both of which are a function of the communication between, and the cognition of, the individuals that constitute the groups. We have two goals in mind while reaching our milestones: intellectual merit and the broader impact. For intellectual merit, this research will contribute to our understanding of how events, social, and cognitive factors from past group formations affect future group formations. As for the broader impact, the model develop will help inform mathematical models of new group formation.