Data-driven psychophysical methods to diversify SIAs and address bias

TL;DR

This paper introduces a data-driven method to make Socially Interactive Agents more inclusive and culturally adaptive by modeling user expectations and preferences.

Contribution

The novel use of reverse correlation in psychophysics to diversify SIAs and reduce bias in human-AI interactions.

Findings

Reverse correlation can model user perceptual expectations and sociocultural norms.

Integrating these insights improves SIA design for cultural inclusivity and user trust.

The method supports broader efforts to reduce algorithmic bias and access inequality.

Abstract

To realize their full potential, Socially Interactive Agents (SIAs) must effectively engage with human users from diverse individual, social, and cultural backgrounds. However, most current SIAs are grounded in White- and Western-centric assumptions, limiting their ability to express and interpret social cues appropriately across cultures. Here, we demonstrate how the data-driven psychophysical method of reverse correlation can help address these limitations by modeling users’ perceptual expectations, preferences, and sociocultural norms and strategically integrating these insights into SIA design. Drawing on examples from our research group, we show how this method could enable SIAs to exhibit social signals that are psychologically grounded, culturally adaptive, and ethnically inclusive. By informing the design of SIA appearance and expressive behavior with empirically derived user models, our approach aims to improve user engagement and trust while contributing to broader efforts to mitigate algorithmic bias, reduce access inequality, and challenge real-world prejudice in both human-AI and human–human interaction contexts.

Figures