Title :
Resource systems in games: An analytical approach
Author :
Justinussen, Tróndur ; Rasmussen, Peter Hald ; Canossa, Alessandro ; Togelius, Julian
Author_Institution :
IT Univ. of Copenhagen, Copenhagen, Denmark
Abstract :
We describe an approach to using standard data mining algorithms to help analyse recurring themes in game design across several games, and to help suggest novel game design ideas. This is illustrated with the analysis of 119 different resource systems across 20 games. Clustering is used to validate the assignment of resources into archetypes; frequent pattern mining is used to find commonly co-occurring resource attributes; and decision tree induction is used to visualize the relations between resource archetypes. We discuss the relation between qualitative and quantitative analysis of game design and suggest that qualitative analysis is necessary but that quantitative methods can be of invaluable help.
Keywords :
computer games; data mining; data visualisation; decision trees; pattern clustering; analytical approach; data clustering; data mining algorithms; data visualization; decision tree induction; frequent pattern mining; game design; qualitative analysis; quantitative analysis; recurring theme analysis; resource archetype assignment validation; resource attribute cooccurrence; resource systems; Abstracts; Avatars; Clustering algorithms; Data mining; Dynamic scheduling; Games; Generators;
Conference_Titel :
Computational Intelligence and Games (CIG), 2012 IEEE Conference on
Conference_Location :
Granada
Print_ISBN :
978-1-4673-1193-9
Electronic_ISBN :
978-1-4673-1192-2
DOI :
10.1109/CIG.2012.6374153
