Modeling Individual and Team Behavior through Spatio-temporal Analysis

TL;DR

This paper introduces Interactive Behavior Analytics (IBA), a new methodology combining visualization, labeling, and clustering algorithms to model and interpret individual and team behaviors in multiplayer games.

Contribution

The paper presents IBA, a comprehensive framework integrating visualization, labeling, and clustering for analyzing spatio-temporal game data, which is novel in this context.

Findings

Effective modeling of team and individual behaviors

Human-interpretable behavior models developed

Validated on data from BoomTown and DotA 2

Abstract

Modeling players' behaviors in games has gained increased momentum in the past few years. This area of research has wide applications, including modeling learners and understanding player strategies, to mention a few. In this paper, we present a new methodology, called Interactive Behavior Analytics (IBA), comprised of two visualization systems, a labeling mechanism, and abstraction algorithms that use Dynamic Time Warping and clustering algorithms. The methodology is packaged in a seamless interface to facilitate knowledge discovery from game data. We demonstrate the use of this methodology with data from two multiplayer team-based games: BoomTown, a game developed by Gallup, and DotA 2. The results of this work show the effectiveness of this method in modeling, and developing human-interpretable models of team and individual behavior.