Discovering social and aesthetic categories of avatars : a bottom-up artificial intelligence approach using image clustering

Abstract

Videogame avatars are more than visual artifacts—they express cultural norms and expectations from both the real world and the fictional world. In this paper, we describe how artificial intelligence clustering can automatically discover distinct characteristics of players’ avatars without prior knowledge of a system’s underlying data structures. Using only avatar images collected from a study with 191 players, we applied two clustering techniques— namely non-negative matrix factorization and archetypal analysis—that automatically revealed and detected (1) an avatar’s gender, (2) regions that appeared to isolate shapes of items and accessories, and (3) aesthetic preferences for particular colors (e.g., bright or muted) and shapes for different body parts. These clusters correlated with players’ preferences for character abilities, e.g., male avatars in dark clothes correlated with having high physical but low magic-casting attributes. These findings show that a bottom-up analysis of images can reveal explicit categories like gender, but also implicit categories like preferences of players. We believe that such computational approaches can enable developers to (1) better understand players’ desires and needs, (2) quantitatively view how systems may be limited in supporting players, and (3) find actionable solutions for these limitations.