Abstract— This paper introduces quantitative measurements/metrics of qualitative entertainment features within interactive playgrounds inspired by computer games and proposes artificial intelligence (AI) techniques for optimizing entertainment in such interactive systems. For this purpose the innovative Playware playground is presented and a quantitative approach to entertainment modeling based on psychological studies in the field of computer games is introduced. Evolving artificial neural networks (ANNs) are used to model player satisfaction (interest) in real-time and investigate quantitatively how the qualitative factors of challenge and curiosity contribute to human entertainment according to player reaction time with the game. The limitations of the methodology and the extensibility of the proposed approach to other genres of digital entertainment are discussed.
Georgios N. Yannakakis, Henrik Hautop Lund, John H