Distributional Concept Analysis

Abstract

This article proposes a novel computational method for discerning the structure and history of concepts. Based on the analysis of co-occurrence data in large data sets, the method creates a measure of “binding” that enables the construction of verbal constellations that comprise the larger units, “concepts,” that change over time. In contrast to investigation into semantic networks, our method seeks to uncover structures of conceptual operation that are not simply semantic. These larger units of lexical operation that are visualized as interconnected networks may have underlying rules of formation and operation that have as yet unexamined—perhaps tangential—connection to meaning as such. The article is thus exploratory and intended to open the history of concepts to some new avenues of investigation.