A bottom-up method for developing a trait-based model of player behavior

Abstract

Understanding player behavior through telemetry logs is an important yet unresolved problem. Interpreting the meaning of players' low-level behaviors over time is important due to its utility in (a) developing a more adaptive and personalized game experience, (b) uncovering game design issues, and (c) understanding the human cognitive processes in a gaming context, not to mention its use and application to learning, training, and health. In this paper, the authors describe a work in progress developing a quantified model of player behavior for interpreting telemetry data from a first-person roll-playing game (RPG). This kind of model constitutes a grammar that will allow us to make sense of low-level behavioral data to assess personality, decision-making, and other cognitive constructs through behavioral measures.