Game Analytics pp 255-283 | Cite as

Meaning in Gameplay: Filtering Variables, Defining Metrics, Extracting Features and Creating Models for Gameplay Analysis

Chapter

Abstract

Analyzing game-related data, at its core, is a process that involves being able to articulate knowledge and meaning from apparently meaningless data. Analysis often consists of imposing order, establishing categories and seeing patterns in disorderly, continuous and heterogeneous streams of information, especially when dealing with gameplay telemetry data, which directly emanates from players’ behavior. Since human behavior represents the response of an organism to its ecosystem, it possesses no intrinsic meaning; rather it needs to be interpreted. It is mostly through interpretation of data that actionable knowledge and pertinent meaning can be massaged into existence according to the assumption that player motivations, desires, beliefs and personality are encoded in a player’s behavior and it is sufficient to interpret metrics data to unravel extensive information about players. Ludwig Wittgenstein, in his Tractatus logico-philosophicus, (Wittgenstein 2001) said that “the limits of my language mean the limits of my world” implying that the logical possibilities available within a certain domain are constrained by the language used to talk about such a domain. In the specific case of game data analysis, the verbs used to talk about player behavior are defined by the game variables measured and tracked by the telemetry system. These variables, once measured, become metrics, and from metrics, features are extracted; the selection of which features to use is a pivotal component of game data analysis. This chapter presents strategies to aid in this process, specifically, in the selection of variables, their measurement and the treatment of the resulting features to obtain meaningful models. The process of selecting game variables to be monitored for further analysis is not a trivial one since it is exactly this process of selection that defines which analyses can be carried out and enables analysts to draw inferences from the game.

Notes

References

  1. Allport, G. (1936). Personality: A psychological interpretation. New York: Holt, Rinehart, & Winston publishers.Google Scholar
  2. Bartle, R. (1996). Hearts, clubs, diamonds, spades: Players who suit MUDs. Journal of MUD research, 1(1), 19.Google Scholar
  3. Blomkvist, S. (2002). Persona – An overview. In Theoretical perspectives in human-computer interaction. Stockholm, IPLab, KTH.Google Scholar
  4. Brudvig, E. (2010). Halo: Reach post-beta interview. IGN. Retrieved June 6, 2010.Google Scholar
  5. Canossa, A. (2009). Play persona: Modeling player behaviour in computer games. The Royal Danish Academy of Fine Arts, School of Design/IO Interactive. Ph.D. thesis, Supervisor: Dr. Troels Degn Johansson, Denmark.Google Scholar
  6. Canossa, A., & Drachen, A. (2009a). Patterns of play: Play-personas in user-centered game development. In Proceedings of DIGRA 2009. London, United Kingdom:DiGRA Publishers.Google Scholar
  7. Canossa, A., & Drachen, A. (2009b). Play-personas: Behaviors and belief systems in user-centered game design. In Proceedings of INTERACT 2009 (LNCS vol. 5727, pp. 510–523). Uppsala, Sweden: Springer.Google Scholar
  8. Charles, D., & Black, M. (2004, November). Dynamic player modeling: A framework for player-centered digital games. In Proceedings of the international conference on computer games: Artificial intelligence, design and education (pp. 29–35).Google Scholar
  9. Charles, D., Mcneill, M., Mcalister, M., Black, M., Moore, A., Stringer, K. Kücklich, J., & Kerr, A. (2005). Player-centred game design: Player modelling and adaptive digital games. In Digital games research association 2005 conference: Changing views – Worlds in play, Vancouver.Google Scholar
  10. Cooper, A. (2004). The inmates are ruling the asylum. Indianapolis: Sams Publishing.Google Scholar
  11. Cooper, A., Reimann, R., & Cronin, D. (2007). About face 3: The essentials of interaction design. Indianapolis: Wiley.Google Scholar
  12. Costa, P. T., & McCrae, R. R. (1985). The NEO personality inventory manual. Odessa: Psychological Assessment Resources.Google Scholar
  13. Costa, P. T., & McCrae, R. R. (1992). Revised NEO personality inventory (NEO-PI-R) and NEO five-factor inventory (NEO-FFI) manual. Odessa: Psychological Assessment Resources.Google Scholar
  14. Drachen, A., & Canossa, A. (2009). Towards gameplay analysis via gameplay metrics. In Proceedings of the 13th MindTrek. Tampere: ACM-SIGCHI Publishers.Google Scholar
  15. Drachen, A., Canossa, A., & Yannakakis, G. (2009). Player modeling using self-organization in Tomb Raider: Underworld. In Proceedings of the IEEE computational intelligence in games (pp. 1–8). Milan: IEEE Publishers.Google Scholar
  16. Edmunds, A., & Morris, A. (2000). The problem of information overload in business organisations: a review of the literature. International Journal of Information Management, 20(1), 17–28. ISSN:0268–4012, doi:10.1016/S0268-4012(99)00051-1, URL: http://www.sciencedirect.com/science/article/pii/S0268401299000511 Google Scholar
  17. Gagné, A., Seif El-Nasr, M., & Shaw, C. (2011). A deeper look at the use of telemetry for analysis of player behavior in RTS games. Entertainment Computing–ICEC 2011, 6972, 247–257.Google Scholar
  18. Gagné, A., Seif El-Nasr, M., & Shaw, C. (2012). Analysis of telemetry data from a real-time ­strategy game: A case study. ACM Computers in Entertainment, 10 (3), Article No. 2. doi:http://10.1145/2381876.2381878, http://doi.acm.org/
  19. Goldberg, L. R. (1993). The structure of phenotypic personality traits. American Psychologist, 48, 26–34.CrossRefGoogle Scholar
  20. Goldberg, L. R. (2001). Personality processes and individual differences – An alternative description of personality: The big-five factor structure. In S. E. Hyman (Ed.), The science of mental health. New York: Routledge.Google Scholar
  21. Han, J., & Kamber, M. (2006). Data mining: Concepts and techniques (Second Editionth ed.). San Francisco: Morgan Kaufman Publishers.MATHGoogle Scholar
  22. Houlette, R. (2003, December). Player modeling for adaptive games. In S. Rabin (Ed.), AI game programming wisdom 2. Hingham: Charles River Media.Google Scholar
  23. Hunicke, R., LeBlanc, M., & Zubek, R. (2004). MDA: A formal approach to game design and game research. In Proceedings of the challenges in game AI workshop, 19th national conference on artificial intelligence AAAI’04. San Jose: AAAI Press.Google Scholar
  24. John, O. P., Angleitner, A., & Ostendorf, F. (1988). The lexical approach to personality: A historical review of trait taxonomic research. European Journal of Personality, 2(3), 171–203. Wiley, Universität Bielefeld, Federal Republic of Germany.Google Scholar
  25. Mahlman, T., Drachen, A., Canossa, A., Togelius, J., & Yannakakis, G. N. (2010). Predicting player behavior in Tomb Raider: Underworld. In Proceedings of the 2010 IEEE conference on computational intelligence in games (pp. 178–185). Copenhagen: IEEE Publishers.Google Scholar
  26. Martínez, H. P., & Yannakakis, G. N. (2010, October). Genetic search feature selection for affective modeling: A case study on reported preferences. In Proceedings of the 3rd international workshop on Affective interaction in natural environments (pp. 15–20). New York: ACM.Google Scholar
  27. Pincus, M., & Gordon, B. (2009). Ghetto testing and minimum viable products. Lecture at Stanford Technology Ventures Program, Stanford Uni versity.Google Scholar
  28. Pruitt, J., & Grudin, J. (2003, June). Personas: Practice and theory. In Proceedings of the 2003 conference on designing for user experiences (pp. 1–15). San Francisco: ACM.Google Scholar
  29. Salen, K., & Zimmerman, E. (2003). Rules of play: Game design fundamentals. Cambridge: The MIT Press.Google Scholar
  30. Schell, J. (2008, August). The art of game design: A book of lenses (p. 99). Amsterdam: Morgan Kaufmann.Google Scholar
  31. Smith, A. M., Lewis, C., Hullett, K., Smith, G., & Sullivan, A. (2011, July). An inclusive view of player modeling. 6th international conference on Foundations of Digital Games (FDG 2011), Bordeaux, France.Google Scholar
  32. Sydney Morning Herald (2010, May 25). Millions reach for ‘Halo’. Sydney Morning Herald. Retrieved June 6, 2010.Google Scholar
  33. Thurau, C., & Drachen, A. (2011). Introducing archetypal analysis for player classification in games. EPEX Workshop in FDG 2011, Bordeaux.Google Scholar
  34. Tychsen, A., & Canossa, A. (2008). Defining personas in games using metrics. In Proceedings of FUTURE PLAY 2008 (pp. 73–80). Toronto: ACM publishers.Google Scholar
  35. Wittgenstein, L. (2001). Tractatus logico-philosophicus (2nd ed.). London: Routledge.Google Scholar
  36. Wong, C., Kim, J., Han, E., & Jung, K. (2009). Human-centered modeling for style-based adaptive games. Journal of Zhejiang University – SCIENCE A, 10(4), 530–534.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London 2013

Authors and Affiliations

  1. 1.College of Arts, Media and DesignNortheastern UniversityBostonUSA
  2. 2.Center for Computer Games ResearchIT University of CopenhagenCopenhagenDenmark

Personalised recommendations