Player modeling using self-organization in Tomb Raider: Underworld

By Anders Drachen, Alessandro Canossa, Georgios N. Yannakakis. 2009 IEEE Symposium on Computational Intelligence and Games, 2009

326 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Guns, swords and data: Clustering of player behavior in computer games in the wild (2012, methodology): “There are several major challenges, notably: 1) The potential extreme highdimensionality of the behavioral data [1] [33] [34] [38]; 2) It can be necessary to mix datatypes, e.g. binominal, categorical and numerical values, in the same analysis, in order to include all the necessary behavioral…”
Guns and guardians: Comparative cluster analysis and behavioral profiling in destiny (2016, methodology): “de Behavioral profiling in games has previously been performed using a variety of descriptive and statistical techniques, as well as machine learning, the latter with an emphasis on unsupervised techniques due to the common explorative goal of profiling in games [8], [2], [22].”
Introducing Archetypal Analysis for Player Classification in Games (2011, methodology): “Non-negative Matrix Factorization (NMF) [14], Self-Organizing Networks (SOM)) [7, 1].”
Player Types: A Meta-synthesis (2014, background): “and gaming intensity (Ip & Jacobs 2005; Drachen et al. 2009; Hamari & Lehdonvirta 2010; Tseng 2010; Kallio et al. 2011). Some works, such as Yee (2006) and Kallio et al. (2011) do provide sub-dimension to the higher abstraction level player motivation and mentalities; however, on this abstraction le”