Understanding the Cognitive Complexity in Language Elicited by Product Images

TL;DR

This paper introduces a scalable method to measure and validate the cognitive complexity of language elicited by product images, using a large dataset and language models to approximate human judgments.

Contribution

It presents a novel approach for quantifying cognitive complexity in language responses to product images, including a new dataset and validation with language models.

Findings

Human-rated complexity can be approximated by language models.

The approach is minimally supervised and scalable.

Cognitive complexity predicts consumer choices.

Abstract

Product images (e.g., a phone) can be used to elicit a diverse set of consumer-reported features expressed through language, including surface-level perceptual attributes (e.g., "white") and more complex ones, like perceived utility (e.g., "battery"). The cognitive complexity of elicited language reveals the nature of cognitive processes and the context required to understand them; cognitive complexity also predicts consumers' subsequent choices. This work offers an approach for measuring and validating the cognitive complexity of human language elicited by product images, providing a tool for understanding the cognitive processes of human as well as virtual respondents simulated by Large Language Models (LLMs). We also introduce a large dataset that includes diverse descriptive labels for product images, including human-rated complexity. We demonstrate that human-rated cognitive complexity can be approximated using a set of natural language models that, combined, roughly capture the complexity construct. Moreover, this approach is minimally supervised and scalable, even in use cases with limited human assessment of complexity.