Fuzzy Affective Player Models: A Physiology-Based Hierarchical Clustering Method

Authors

  • Pedro Nogueira University of Porto
  • Rúben Aguiar Universidade do Porto
  • Rui Rodrigues INESC-TEC / University of Porto
  • Eugénio Oliveira University of Porto
  • Lennart Nacke University of Ontario

DOI:

https://doi.org/10.1609/aiide.v10i1.12719

Keywords:

biofeedback, games, emotional regulation, physiology, affective player modelling

Abstract

Current approaches to game design improvements rely on time-consuming gameplay testing processes, which rely on highly subjective feedback from a target audience. In this paper, we propose a generalizable approach for building predictive models of players’ emotional reactions across different games and game genres, as well as other forms of digital stimuli. Our input agnostic approach relies on the following steps: (a) collecting players' physiologically-inferred emotional states during actual gameplay sessions, (b) extrapolating the causal relations between changes in players' emotional states and recorded game events, and (c) building hierarchical cluster models of players' emotional reactions that can later be used to infer individual player models via fuzzy cluster membership vectors. We expect this work to benefit game designers by accelerating the affective play-testing process through the offline simulation of players' reactions to game design adaptations, as well as to contribute towards individually-tailored affective gaming.

Downloads

Published

2021-06-29

How to Cite

Nogueira, P., Aguiar, R., Rodrigues, R., Oliveira, E., & Nacke, L. (2021). Fuzzy Affective Player Models: A Physiology-Based Hierarchical Clustering Method. Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, 10(1), 132-138. https://doi.org/10.1609/aiide.v10i1.12719