Measuring Memberships in Collectives in Light of Developments in Cognitive Science and Natural-Language Processing

Abstract

Which individuals and corporate actors belong in a collective, and who decides? Sociology has not had good analytical tools for addressing these questions. Recent work that adapts probabilistic representations of concepts and probabilistic categorization to sociological research opens opportunities for making progress on the measurement of memberships. It turns out that the probabilistic cognitive-based reformulation reveals unexpected connections to language models and natural-language processing. In particular, the leading probabilistic classifier BERT provides new and powerful ways to measure core concepts.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 7 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.