Predictive Analytics

Predictive capabilities for social diffusion processes, for instance to permit early identification of emerging contentious situations, rapid detection of disease outbreaks, or accurate forecasting of the ultimate reach of potentially “viral” ideas or behaviors, are critically important for both national and global security. An enormous volume of security-relevant information is present on the Web, for instance in the content produced each day by millions of bloggers worldwide, but discovering and making sense of these data is very challenging. Detecting and characterizing emerging topics of discussion and consumer trends through analysis of Internet data is also of great interest to businesses. Non-equilibrium social science emphasizes dynamical phenomena, for instance the way political movements emerge or competing organizations interact.

This research and development involves web analysis, security informatics, network analysis, text analysis, supervised/unsupervised learning, cyber security, sentiment analysis, social media analysis, machine learning, sociological models, and social network modeling.

Publications

• Estimating the sentiment of social media content for security informatics applications documents our analysis of the utility of two computational methods for estimating social media sentiment and illustrates their potential for security informatics by estimating regional public opinion regarding two events: the 2009 Jakarta hotel bombings and 2011 Egyptian revolution.

  • Glass K and Colbaugh R,  Estimating the sentiment of social media content for security informatics applications, Security Informatics 2012, 1:3 http://www.security-informatics.com/content/1/1/3

• Leveraging Sociological Models for Predictive Analytics demonstrates that sociologically-grounded learning algorithms outperform gold-standard methods in three important and challenging tasks: 1) inferring the (unobserved) nature of relationships in adversarial social networks, 2) predicting whether nascent social diffusion events will “go viral”, and 3) anticipating and defending future actions of opponents in adversarial settings. Significantly, the new algorithms perform well even when there is limited data available for their training and execution.

  • Colbaugh R and Glass K, Leveraging Sociological Models for Predictive Analytics, 2012

• Early Warning Analysis for Social Diffusion Events documents a new approach to the predictive analytics problem, in which analysis of meso-scale network dynamics is leveraged to generate useful predictions for complex social phenomena. We find that the outcomes of social diffusion processes may depend crucially upon the way the early dynamics of the process interacts with the underlying network’s community structure and core-periphery structure.

  • Colbaugh R and Glass K, Early Warning Analysis for Social Diffusion Events, 2012

• Predictive Non-Equilibrium Social Science argues that predictive analysis is an essential element of non-equilibrium social science, occupying a central role in its scientific inquiry and representing a key activity of practitioners in domains such as economics, public policy, and national security.

  • Colbaugh R, Glass K and Johnson C, Predictive Non-Equilibrium Social Science, Proceedings of the 2012 Winter Simulation Conference, C. Laroque, J. Himmelspach, R. Pasupathy, O. Rose, and A.M. Uhrmacher, eds., 2012

• Web Analytics for Security Informatics considers the problem of exploring and analyzing the Web to realize three fundamental objectives: 1.) security-relevant information discovery; 2.) target situational awareness, typically by making (near) real-time inferences concerning events and activities from available observations; and 3.) predictive analysis, to include providing early warning for crises and forming predictions regarding likely outcomes of emerging issues and contemplated interventions.

  • Glass K and Colbaugh R, Web Analytics for Security Informatics, 2011

• Emerging Topic Detection for Business Intelligence via Predictive Analysis of ‘Meme’ Dynamics considers the problem of monitoring the Web to spot emerging memes – distinctive phrases which act as “tracers” for topics – as a means of early detection of new topics and trends. The utility of meme dynamics prediction methodology is demonstrated through analysis of a sample of 200 memes which emerged online during the second half of 2008.

  • Colbaugh R and Glass K, Emerging Topic Detection for Business Intelligence via Predictive Analysis of ‘Meme’ Dynamics, 2011