Comparing scalable strategies for generating numerical perspectives

TL;DR

This paper compares three scalable methods for generating numerical perspectives to help people understand large or unfamiliar numbers, highlighting their strengths and user preferences.

Contribution

It introduces and evaluates a rule-based, crowdsourced, and semantic similarity-based approach for large-scale perspective generation, demonstrating their combined effectiveness.

Findings

Combined approaches outperform individual methods

Different approaches excel in different contexts

Users have heterogeneous preferences for perspectives

Abstract

Numerical perspectives help people understand extreme and unfamiliar numbers (e.g., \$330 billion is about \$1,000 per person in the United States). While research shows perspectives to be helpful, generating them at scale is challenging both because it is difficult to identify what makes some analogies more helpful than others, and because what is most helpful can vary based on the context in which a given number appears. Here we present and compare three policies for large-scale perspective generation: a rule-based approach, a crowdsourced system, and a model that uses Wikipedia data and semantic similarity (via BERT embeddings) to generate context-specific perspectives. We find that the combination of these three approaches dominates any single method, with different approaches excelling in different settings and users displaying heterogeneous preferences across approaches. We conclude by discussing our deployment of perspectives in a widely-used online word processor.