PhD Candidate, Austin Kozlowski from the University of Chicago will be presenting on Computational Sociology.
Abstract: Theories of culture have long relied on spatial metaphors to describe how meaning systems are internally organized. Constrained by limitations of data and visualization, prior spatial models of meaning have commonly taken the form of two-dimensional “maps” that can be easily rendered on paper. However, recent advances in computational linguistics and text analysis show that the vast array of semantic associations that characterize a cultural system can only be effectively represented by expansive models with hundreds of dimensions. In this talk, I outline how we may harness such high-dimensional models to study cultural systems structurally and holistically. Focusing on collective understandings of class and politics, I put forth methods to identify periods when cultural systems undergo structural shifts.
Bio: "Kozlowski uses computational and statistical methods to study the relationship between culture and politics. His research focuses on the questions of how belief systems are structured and why certain ideas seem to "go together." By developing new methods and adapting novel data sources, he attempts to shed new light on these age-old questions from the sociology of knowledge and culture. In previous work, he developed ways to use word embedding models to discover cultural categories and associations in text. Kozlowski have also examined political conservatives' loss of trust in scientists, the role ideology plays in shaping economists' expert opinions, and the evolving patterns of political alignments in the American public. In his dissertation, he applies word embedding models as well as qualitative approaches and methods drawn from bioinformatics to understand how historic cultural divisions have become mapped onto current political divides in the United States."