A Multidimensional Framework for Evaluating Lexical Semantic Change with Social Science Applications

TL;DR

This paper introduces a three-dimensional framework for evaluating lexical semantic change, integrating sentiment, breadth, and intensity shifts, with applications in social science and an illustrative case study on mental health terminology.

Contribution

It proposes a novel multidimensional framework and computational methodology for analyzing lexical semantic change across multiple aspects simultaneously.

Findings

Semantic shifts in mental health terms reveal patterns of stigma and concept creep.

The framework effectively maps semantic change systematically and economically.

Application demonstrates relevance to social science issues.

Abstract

Historical linguists have identified multiple forms of lexical semantic change. We present a three-dimensional framework for integrating these forms and a unified computational methodology for evaluating them concurrently. The dimensions represent increases or decreases in semantic 1) sentiment, 2) breadth, and 3) intensity. These dimensions can be complemented by the evaluation of shifts in the frequency of the target words and the thematic content of its collocates. This framework enables lexical semantic change to be mapped economically and systematically and has applications in computational social science. We present an illustrative analysis of semantic shifts in mental health and mental illness in two corpora, demonstrating patterns of semantic change that illuminate contemporary concerns about pathologization, stigma, and concept creep.