[Paper Review] Short Literature Review for a General Player Model Based on Behavlets

Benjamin Ultan Cowley, Darryl Charles|arXiv (Cornell University)|Mar 22, 2016

Sports Analytics and Performance36 references3 citations

TL;DR

This paper proposes a foundational framework for a generalized player model by integrating player psychology, game structure, and experiential frameworks. It introduces a scoping review to identify core tools for modeling player experience, with the goal of enabling more accurate, psychology-informed player modeling that supports adaptive AI in games.

ABSTRACT

We present the first in a series of three academic essays which deal with the question of how to build a generalized player model. We begin with a proposition: a general model of players requires parameters for the subjective experience of play, including at least: player psychology, game structure, and actions of play. Based on this proposition, we pose three linked research questions, which make incomplete progress toward a generalised player model: RQ1 what is a necessary and sufficient foundation to a general player model?; RQ2 can such a foundation improve performance of a computational intelligence-based player model?; and RQ3 can such a player model improve efficacy of adaptive artificial intelligence in games? We set out the arguments behind these research questions in each of the three essays, presented as three preprints. The first essay, in this preprint, reviews the literature for the core foundations for a general player model. We then propose a plan for future work to systematically extend the review and thus provide an empirical answer to RQ1 above. This work will directly support the proposed approach to address RQ2 and RQ3 above. This review was developed to support our 'Behavlets' approach to player modelling; therefore if citing this work, please use the relevant citation: Cowley B, Charles D. Behavlets: a Method for Practical Player Modelling using Psychology-Based Player Traits and Domain Specific Features. User Modelling and User-Adapted Interaction. 2016 Feb 8; online (Special Issue on Personality in Personalized Systems):1-50.

Motivation & Objective

• To establish a necessary and sufficient foundation for a generalized player model that captures the subjective experience of play.
• To identify and evaluate existing tools from player psychology, game structure, and experiential frameworks as potential building blocks for such a model.
• To lay the groundwork for systematic review and meta-analysis to empirically validate the most effective components for player modeling.
• To support the development of more adaptive and personalized game AI by grounding player models in validated psychological and design theories.

Proposed method

• Conducting a non-systematic, on-demand scoping review of literature in three core areas: player psychology, game structure, and experiential frameworks.
• Identifying key references and search terms related to player typologies, game design patterns, and psychological models of behavior.
• Proposing a future research plan to transform the scoping review into a systematic review with replicable search strategies and filtering procedures.
• Using indexed databases like ACM Digital Library to collect citing articles for key works, particularly focusing on published player models and typologies.
• Designing a methodological pipeline to enable meta-analysis of existing models, including quantitative assessment of classifier accuracy and model efficacy.
• Integrating findings into the Behavlets framework, which links psychological traits and domain-specific game features to create richer, theory-based player modeling features.

Experimental results

Research questions

• RQ1 What existing tools for describing player experience constitute a necessary and sufficient foundation for a generalized player model?
• RQ2 Can such a foundation improve the performance of computational intelligence-based player models in real-time settings?
• RQ3 Can a psychologically grounded player model enhance the efficacy and adaptability of AI in games?

Key findings

• Existing player models often fail to capture psychological dimensions of play, relying instead on basic in-game variables and challenge tuning.
• Player typologies such as Bartle’s are frequently cited but lack systematic validation, with limited evidence on their accuracy in classifying player behavior.
• The Behavlets framework offers a novel approach by linking psychological traits and game design patterns to create theory-informed modeling features.
• There is a significant gap in the literature for systematic, replicable reviews of player modeling tools, especially in non-medical domains like game AI.
• A future systematic review and meta-analysis could quantitatively assess the efficacy of different foundational elements, such as the accuracy of models using Bartle’s typology.
• The integration of psychological theory with game design patterns and action modeling can lead to more robust and generalizable player models.