The Institute for Mathematical Behavioral Sciences Colloquium Series presents

“Political Dynamics in Large Scale Web Data Sets: A Study of Content-Oriented Behavior”
with Roja Bandari, Complex Network Groups, UCLA

Thursday, May 8, 2014
4:00–5:00 p.m.
Social Science Plaza A, Room 2112

Despite large investments by industry and the expanding body of research on "big data" in academia, gaining insight into collective behavior online has been elusive due to the considerable computational challenges posed by the scale, complexity, and the inevitable noisiness of the associated data sets. These obstacles hinder hopes that internet-scale data could proliferate data-driven models in the Social Sciences.

This talk addresses this pressing problem and offers an approach to extracting macro structures of collective behavior resulting from complex social phenomena in large datasets. The approach involves extracting structures from aggregated user actions, finding possible meanings, and arranging data in layers so that it is iteratively explorable by scientists. Applying this methodology to four years of data from a political social news site reveals a wholly new perspective, featuring distinct political preferences and vividly captures the transformative effect of a contentious political event. The derived themes are not only statistically significant, but also meaningful to human understanding. The approach is scalable, provides a compelling summary of the corpus, and has the potential to apply to different contexts.

For further information, please contact Joanna Kerner, kernerj@uci.edu or 949-824-8651.