User Modeling and User-Adapted Interaction

, Volume 23, Issue 5, pp 489–526

Real-time rule-based classification of player types in computer games

  • Ben Cowley
  • Darryl Charles
  • Michaela Black
  • Ray Hickey
Original Paper


The power of using machine learning to improve or investigate the experience of play is only beginning to be realised. For instance, the experience of play is a psychological phenomenon, yet common psychological concepts such as the typology of temperaments have not been widely utilised in game design or research. An effective player typology provides a model by which we can analyse player behaviour. We present a real-time classifier of player type, implemented in the test-bed game Pac-Man. Decision Tree algorithms CART and C5.0 were trained on labels from the DGD player typology (Bateman and Boon, 21st century game design, vol. 1, 2005). The classifier is then built by selecting rules from the Decision Trees using a rule- performance metric, and experimentally validated. We achieve ~70% accuracy in this validation testing. We further analyse the concept descriptions learned by the Decision Trees. The algorithm output is examined with respect to a set of hypotheses on player behaviour. A set of open questions is then posed against the test data obtained from validation testing, to illustrate the further insights possible from extended analysis.


Player typology Player profiling Computer games Decision trees Classification Experimental validation 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Supplementary material

11257_2012_9126_MOESM1_ESM.doc (43 kb)
ESM 1 (DOC 43 kb)


  1. Acuña D.E., Parada V.: People efficiently explore the solution space of the computationally intractable traveling salesman problem to find near-optimal tours. PloS one 5(7), e11685 (2010)CrossRefGoogle Scholar
  2. Anscombe F.J.: Graphs in statistical analysis. Am. Stat. 27(1), 17–21 (1973)Google Scholar
  3. Anyanwu M., Shiva S.: Comparative analysis of serial decision tree classification algorithms. Int. J. Comput. Sci. Secur. 3(3), 230–240 (2009)Google Scholar
  4. Bartle, R.: Hearts, clubs, diamonds, spades: players who suit MUDs. J. Virtual Environ. 1(1) (1996)Google Scholar
  5. Bateman C., Boon R.: 21st Century Game Design, vol. 1. Charles River Media, Londan (2005)Google Scholar
  6. Bateman, C., Lowenhaupt, R., Nacke, L.: Player typology in theory and practice. In: Proceedings of DiGRA: Think Design Play 2011. Utrecht, The Netherlands (2011)Google Scholar
  7. Baumgarten, R.: Towards automatic player behaviour characterisation using multiclass linear discriminant analysis. In: Proceedings of the Artificial Intelligence and Simulation of Behaviour Symposium: AI and Games, March 2010. De Montfort University, Leicester, UK (2010)Google Scholar
  8. Beal, C., Beck, J., Westbrook, D., Atkin, M., Cohen, P.: Intelligent modeling of the user in interactive entertainment. In: Forbus, K., El-Nasr, M.S. (eds.) Artificial Intelligence and Interactive Entertainment II. Papers from the AAAI Spring Symposium, Stanford, CA (2002)Google Scholar
  9. Black M., Hickey R.J.: Maintaining the performance of a learned classifier under concept drift. Intell. Data Anal. 3(6), 453–474 (1999)CrossRefGoogle Scholar
  10. Bowling M., Fürnkranz J., Graepel T., Musick R.: Machine learning and games. Mach. Learn. 63(3), 211–215 (2006)CrossRefGoogle Scholar
  11. Breiman L.: Classification and Regression Trees. Wadsworth International Group, Belmont (1984)MATHGoogle Scholar
  12. Caillois R.: Man, Play, and Games. Free Press of Glencoe, New York (1961)Google Scholar
  13. Chaperot, B., Fyfe, C.: Improving artificial intelligence in a motocross game. In: Proceedings of IEEE Symposium on Computational Intelligence and Games, pp. 181–186 (2006)Google Scholar
  14. Chen G., Liu H., Yu L., Wei Q., Zhang X.: A new approach to classification based on association rule mining. Decis. Support Syst. 42(2), 674–689 (2006)CrossRefGoogle Scholar
  15. Cowley B., Moutinho J., Bateman C., Oliveira A.: Learning principles and interaction design for ‘green my place’: a massively multiplayer serious game. Entertain. Comput. 2(2), 10 (2011)Google Scholar
  16. Cowley, B., Charles, D., Black, M., Hickey, R.: Developing features of game metrics to describe videogame-player behaviour (in preparation, a)Google Scholar
  17. Cowley, B., Kosunen, I., Kivikangas, J. M., Järvelä, S., Lankoski, P., Kemppainen, J.: Machine learning and play patterns: a pilot study for the PPAX framework. J. Simul. Gaming (in preparation, b)Google Scholar
  18. Curtis, P.: Mudding: Social Phenomena in Text-Based Virtual Realities. Intertrek (3), 26–34 (1992).
  19. Drachen, A., Canossa, A.,Yannakakis, G.N.: Player modeling using self-organization in Tomb Raider: Underworld. In: Proceedings of the 5th International Conference on Computational Intelligence and Games, pp. 1–8. IEEE Press, Milano (2009)Google Scholar
  20. Fu D., Houlette R., Rabin S.: Constructing a Decision Tree Based on Past Experience AI Game Programming Wisdom 2, pp. 567–577. Charles River Media, Hingham (2004)Google Scholar
  21. Fürnkranz, J.: Machine learning and game-playing. In: Sammut, C., Webb, G.I. (eds.) Encyclopedia of Machine Learning, pp. 633–637. Springer, New York (2010)Google Scholar
  22. Galway L., Charles D., Black M.: Machine learning in digital games: a survey. Artif. Intell. Rev. 29(2), 123–161 (2008)CrossRefGoogle Scholar
  23. Geisler, B.: An empirical study of machine learning algorithms applied to modelling player behaviour in a first person shooter video game. M.S. thesis, Department of Computer Sciences, University of Wisconsin, Madison (2002)Google Scholar
  24. Grimes, S.: Mining the game: when marketing and gaming meet they do a lot more than advertise. Escapist Magazine, 3, 27 February 2007Google Scholar
  25. Herbrich R., Minka T., Graepel T.: TrueSkill: a Bayesian skill rating system. Adv. Neural Inf. Process. Syst. 19, 569–576 (2007)Google Scholar
  26. Huizinga J.: Homo Ludens: A Study of the Play-Element of Culture. Routledge, London (1949)Google Scholar
  27. Johansson, U., König, R., Niklasson, L.: The truth is in there—rule extraction from opaque models using genetic programming. In: Proceedings of the 17 th International Florida Artificial Intelligence Research Society Conference, FL, p. 113 (2004)Google Scholar
  28. Johansson, U., Sonstrod, C., Niklasson, L.: Explaining winning Poker—a data mining approach. In: Proceedings of the 5th International Conference on Machine Learning and Applications, pp. 129–134. IEEE Computer Society, Washington (2006)Google Scholar
  29. Jones L.: Winning Low-Limit Hold’em. ConJelCo, Pittsburgh (2000)Google Scholar
  30. Jung C.G.: Psychological Types (Collected Works of C.G. Jung, vol. 6). Princeton University Press, Princeton (1971)Google Scholar
  31. Katz-Haas, R.: User-centered design and web development. Usability Interface 5(1), 12–13 (1998)Google Scholar
  32. Kaukoranta, J., Smed, H.: Role of pattern recognition in computer games. In: Sing, L.W., Man, W.H., Wai, W. (eds.) Proceedings of the 2nd International Conference on Application and Development of Computer Games, pp. 189–194. Hong Kong SAR, China (2003)Google Scholar
  33. Kaukoranta T., Smed J., Hakonen H., Rabin S.: Understanding Pattern Recognition Methods. AI Game Programming Wisdom 2, pp. 579–589. Charles River Media, Hingham (2004)Google Scholar
  34. Keirsey D., Bates M.M.: Please Understand Me: Character & Temperament Types. Distributed by Prometheus Nemesis Book Co, Del Mar (1984)Google Scholar
  35. Kennerly, D.: Better game design through data mining. The art and business of making games, Gamasutra (2003).
  36. Kludas, J.: Information fusion for multimedia: exploiting feature interactions for semantic feature selection and construction. PhD thesis, University of Geneva, Geneva (2011)Google Scholar
  37. Kludas J., Bruno E., Marchand-Maillet S.: Can feature information interaction help for information fusion in multimedia problems?. Multimedia Tools Appl. 42(1), 57–71 (2009)CrossRefGoogle Scholar
  38. Levillain, F., Orero, J.O., Rifqi, M., Bouchon-Meunier, B.: Characterizing player’s experience from physiological signals using fuzzy decision trees. In: Proceedings of the IEEE Symposium on Computational Intelligence and Games (CIG), pp. 75–82. IT University of Copenhagen, Denmark (2010)Google Scholar
  39. Ludford, P.J., Terveen, L.G.: Does an individual’s Myers-Briggs type indicator preference influence task-oriented technology use? In: Human-Computer Interaction INTERACT ’03: IFIP, pp. 623–630. IOS Press, Zurich(2003)Google Scholar
  40. Malone, T.W.: What makes things fun to learn? Heuristics for designing instructional computer games. In: Proceedings of the 3rd ACM SIGSMALL Symposium and the First SIGPC Symposium on Small Systems, Palo Alto, CA, pp. 162–169 (1980)Google Scholar
  41. McCrae R.R., Costa P.T. Jr.: Reinterpreting the Myers-Briggs Type indicator from the perspective of the five-factor model of personality. J. Pers. 57(1), 17–40 (1989)CrossRefGoogle Scholar
  42. McGinnis, T., Bustard, D. W., Black, M., Charles, D.: Enhancing e-learning engagement using design patterns from computer games. In: Proceedings of the First International Conference on Advances in Computer–Human Interaction, pp. 124–130. ACM, New York (2008)Google Scholar
  43. Mitchell, T.M.: Machine Learning: McGraw-Hill Higher Education, New York (1997)Google Scholar
  44. Mountain, G.: Psychology Profiling in SILENT HILL: SHATTERED MEMORIES. Video Presented at from the Paris Game/AI Conference, 2010.
  45. Mugambi E.M., Hunter A., Oatley G., Kennedy L.: Polynomial-fuzzy decision tree structures for classifying medical data. Knowledge-Based Syst. 17(2-4), 81–87 (2004)CrossRefGoogle Scholar
  46. Pittenger D.J.: The Utility of the Myers-Briggs type indicator. Rev. Educ. Res. 63(4), 467–488 (1993)CrossRefGoogle Scholar
  47. Quinlan J.R.: C4.5: Programs for Machine Learning. Morgan Kaufmann Publishers, San Mateo (1993)Google Scholar
  48. Ravaja N., Saari T., Turpeinen M., Laarni J., Salminen M., Kivikangas M.: Spatial presence and emotions during video game-playing: does it matter with whom you play?. Presence Teleoper. Virtual Environ. 15(4), 381–392 (2006)CrossRefGoogle Scholar
  49. Salen K., Zimmerman E.: Rules of Play: Game Design Fundamentals, vol. 1. MIT, London (2004)Google Scholar
  50. Sklansky D., Malmuth M.: Hold’em Poker for Advanced Players. Two Plus Two Publishing, Las Vegas (1999)Google Scholar
  51. Thawonmas R., Ho J.-Y.: Classification of online game-players using action transition probability and Kullback Leibler entropy. JACIII 11(3), 319–326 (2007)Google Scholar
  52. Thurau, C., Bauckhage, C.: Smarter team mates: applying hidden Markov models in sports games. In: Proceedings of the SAB Workshop on Adaptive Approaches to Optimizing Player Satisfaction, Roma, Italy, pp. 11–20 (2006)Google Scholar
  53. Tipping, M., Hatton, M.: Drivatar Theory. Online article (2006). Retrieved 7 Sep 2011
  54. Togelius, J., De Nardi, R., Lucas, S.M.: Making racing fun through player modeling and track evolution. In: Proceedings of the SAB Workshop on Adaptive Approaches to Optimizing Player Satisfaction, Roma, Italy, pp. 61–70 (2006)Google Scholar
  55. Tuffery S.: Data Mining and Statistics for Decision Making. Wiley, Chichester (2011)CrossRefMATHGoogle Scholar
  56. Tveit, A., Tveit, G.B.: Game usage mining: information gathering for knowledge discovery in massively multiplayer games. In: Proceedings of the International Conference On Internet Computing (IC’2002), Session On Web Mining, vol. III, pp. 636–642 (2002)Google Scholar
  57. Wong C.-o., Kim J., Jung K., Han E.: Modeling for style-based adaptive games. J. Zhejiang Univ. Sci. A 10(4), 530–534 (2009)CrossRefGoogle Scholar
  58. Zhou, X., Conati, C.: Inferring user goals from personality and behavior in a causal model of user affect. In: Proceedings of the 8th International Conference on Intelligent User Interfaces, pp. 211–218 (2003)Google Scholar

Copyright information

© Springer Science+Business Media B.V. 2012

Authors and Affiliations

  • Ben Cowley
    • 1
    • 3
  • Darryl Charles
    • 2
  • Michaela Black
    • 2
  • Ray Hickey
    • 2
  1. 1.Cognitive Science Unit, Department of Behavioural ScienceUniversity of HelsinkiHelsinkiFinland
  2. 2.School of Computing and Information EngineeringUniversity of UlsterColeraineNorthern Ireland
  3. 3.Center for Knowledge and Innovation ResearchAalto Business School, Aalto UniversityHelsinkiFinland

Personalised recommendations