The extended computational case method: a framework for research design

Abstract

This paper considers the adoption of computational analysis within research designs modeled after the extended case method. Echoing calls to augment the power of contemporary researchers through the adoption of computational text analysis methods, we offer a framework for thinking about how such techniques can be integrated into quasi-ethnographic workflows to address structural sociological claims. We focus, in particular, on how this adoption of novel forms of evidence impacts corpus design and interpretation (which we tie to matters of casing), theoretical elaboration (which we associate to moving empirical claims across scales), and verification (which we see as a process of reflexive scaffolding of theoretical claims). We provide an example of the use of this framework through a study of the marketization of social scientific knowledge in the United Kingdom.

Situated Knowledges and Partial Perspectives: A Framework for Radical Objectivity in Computational Social Science and Computational Humanities

“…Subjective decisions start from the very rst step of computational projects: choosing which data to use and claiming what processes that data capture. 44 Once the data are decided, additional subjective decisions are required throughout computational projects: choosing what to search for in large, complex data requires theory, knowledge, and intuition; which features of the data are used dramatically impacts the resulting representation of the data; choosing an algorithm and parameters alters results; and results on their own are meaning less without some form of interpretation. Because of the sensitivity of computational methods to the content of the data-they are designed to explicitly learn patterns directly from data-each of these subjective decisions directly impacts the patterns identi ed and conclusions drawn.…”