Persona Non Graphica: Visual Representation Biases in Human-Robot Interaction Research

Abstract

Visual representations of "the user" are a key part of academic papers in human-robot interaction (HRI). These visualizations can include photos of participants, drawings of users, or simulated personas. Critical analyses have revealed representation biases in scholarly work, often detectable in formal output like publications. Sampling biases, limitations in demographic reporting, and bias across researchers have been discovered. Yet, no work to date has considered the visualizations (drawings, photos, and other graphical representations) of the human side in the HRI equation. We surface representation biases in work from the flagship ACM/IEEE HRI conference: over-representation of younger light-skinned men with typical bodies, and under-representation of people with darker skin tones, women and gender-diverse people, people with disabilities, and people of various ages and sizes. We critically discuss these trends and offer suggestions for best practices in reporting.