A Simulation-Based Slope Metric for Anchor List Reliability in Word Embedding Spaces

Abstract

Inducing semantic relations in word vector spaces and analyzing how other words or entire documents discursively engage these relations is a popular form of cultural analysis. The authors propose a reliability metric that is easily interpretable and agnostic to the type of relation. The metric, which the authors call the anchor reliability coefficient (relco), is found by creating an artificial document-term matrix of simulated documents that sequentially shift more of their tokens from relation-relevant anchor terms to nonanchor terms and then regressing the documents’ similarity to an induced relation on the anchor inclusion score of the documents. The authors validate the metric at the word level with both expert- and crowdsourced dictionaries and at the document level with expert-annotated social media posts. The authors also provide some heuristic baselines for assessing reliability effect sizes and null hypothesis testing.