Identifying Metaphor Hierarchies in a Corpus Analysis of Finance Articles

TL;DR

This paper analyzes a large corpus of financial news to uncover hierarchical metaphor structures based on the argument-distributions of UP- and DOWN-verbs, revealing organized metaphor hierarchies in financial language.

Contribution

It introduces a corpus-based method using argument-distribution overlap and clustering to identify hierarchical metaphor structures in financial discourse.

Findings

Evidence of organized metaphor hierarchies in financial language

Hierarchical structures derived from argument-distribution analysis

Application of clustering to reveal metaphor groupings

Abstract

Using a corpus of over 17,000 financial news reports (involving over 10M words), we perform an analysis of the argument-distributions of the UP- and DOWN-verbs used to describe movements of indices, stocks, and shares. Using measures of the overlap in the argument distributions of these verbs and k-means clustering of their distributions, we advance evidence for the proposal that the metaphors referred to by these verbs are organised into hierarchical structures of superordinate and subordinate groups.