Predicting Personas Using Mechanic Frequencies and Game State Traces

TL;DR

This paper explores efficient methods to predict player personas from game play traces, comparing supervised learning and sequence models, and highlights the challenges in aligning computational personas with self-reported play styles.

Contribution

Introduces two novel methods for estimating player personas from gameplay data, reducing computational costs and addressing limitations of existing approaches.

Findings

Supervised and sequence learning methods accurately predict procedural personas.

Both methods fail to predict self-reported player-defined play styles.

Highlights the gap between computational personas and player self-perception.

Abstract

We investigate how to efficiently predict play personas based on playtraces. Play personas can be computed by calculating the action agreement ratio between a player and a generative model of playing behavior, a so-called procedural persona. But this is computationally expensive and assumes that appropriate procedural personas are readily available. We present two methods for estimating player persona, one using regular supervised learning and aggregate measures of game mechanics initiated, and another based on sequence learning on a trace of closely cropped gameplay observations. While both of these methods achieve high accuracy when predicting play personas defined by agreement with procedural personas, they utterly fail to predict play style as defined by the players themselves using a questionnaire. This interesting result highlights the value of using computational methods in defining play personas.