Mapping individual concept meanings into shared vector space
Concept Representations in Vector Space: Toward an Interdisciplinary Study of Meaning Variation
Computation and LanguageComputers and Society
Summary
People often think they share the same idea when talking about a concept, but meanings can vary between individuals. The authors developed a way to measure and compare these personal concept meanings by turning written descriptions into math-based points in a shared space. This helps reveal how similar or different people's mental representations of concepts are. They tested their approach using a large dataset of word associations and provided tools for others to do the same.
What this means in practice
- •For natural language processing engineers: Improve algorithms that detect subtle differences in word and concept meanings among different user groups by modeling individual concept variations.
- •For marketing analysts: Analyze how target customer groups differ in their understanding of key brand concepts to tailor messaging more effectively.
Tested on one dataset.
Authors
Simon Josef Durstewitz
Abstract
An increasing number of disciplines recognize the explanatory potential of meaning-bearing mental structures through which individuals interpret the world and guide their behavior. Concept representations constitute a core class of these structures, emerging from individuals' experiences with concept referents and encoding and organizing their understanding of them. Recognizing a private level of meaning, where concepts are not objectively defined by rules in the world but constitute subjective structures in individuals' minds, raises a fundamental question: do different individuals actually mean the same thing when they invoke the same concept? As latent structures, concept representations are difficult to access and model empirically. The present study introduces a measurement framework that makes such representations empirically accessible through textual traces elicited under standardized conditions. Using transformer-based sentence embeddings, the framework maps standardized responses elicited for concepts into a high-dimensional shared vector space, opening concept representations to the systematic analysis of interindividual variation. It develops three analytical avenues: (1) comparing representational sharedness across concepts, (2) identifying variables that correlate with representational variation, and (3) examining how focal actors or subpopulations deviate from a reference population. Each avenue is illustrated through an empirical proof-of-concept drawing on a large-scale free-association dataset. Together, the demonstrations show how researchers from across disciplines can move from a research question and data source to analysis and interpretation. An accompanying GitHub repository provides a ready-to-use implementation of the framework for existing and custom datasets.