The Use of Social Science Methods to Predict Player Characteristics from Avatar Observations

The purpose of this study was to investigate the extent to which real world characteristics of massively multiplayer online role-playing game (MMORPG) players can be predicted based on the characteristics and behavior of their avatars. Ground truth on participants’ real world characteristics was obtained through the administration of validated measures of personality and authoritarian ideology, as well as a demographics form. A team of trained assessors used quantitative assessment instruments to evaluate avatar characteristics, behavior, and personality from a recorded session of the participant’s typical gameplay. The statistical technique of discriminant analysis was then applied to create predictive models for players’ real world characteristics such as gender, approximate age, and education level, using the variables generated through observational assessment of the avatar.