The 21st century has been repeatedly proclaimed to be the century of data. The increasing processing capabilities of computers and the proliferation of Internet-enabled devices have made it easier than ever to gather more and more data about every aspect of our daily lives. The massive amount of data produced every day, however, also needs to be transformed into actual information and knowledge to be of real value and to be of actual use for decision making. This requires adequate techniques and tools that help uncover hidden and valuable information or patterns within the collected data (otherwise, the large volumes of data are just that – data bare any deeper meaning.) This is the goal of data mining1. While data mining has been and is receiving considerable attention to be able to cope with the ever-increasing data volumes, the term has started to appear in the late 1980’s, early 1990’s2. Data mining is not a single technique but rather a conglomerate of methods, techniques, and algorithms, usually applied in an iterative or explorative process.
The 21st century is, however, not only considered to be the age of data mining but has also been coined the ludic century by game designer Eric Zimmerman3 – an age that is characterized by play. It may thus only be fitting that during the last decade or so, data mining has found its way into game production and has become a crucial part of game development and maintenance. This has led to the emergence of the new field of ‘game analytics’ – broadly speaking, the application of analytics to game development and research4. It is “the practice of analyzing recorded game information to facilitate future design decisions”. 5 Game analytics uses data mining techniques to discover patterns and to extract information from game-related data, especially player behavioral data. As it is often the case with new fields, the establishment of game analytics can hardly be tied to a specific point in time or be ascribed to a single factor. Instead, the emergence of game data mining and analytics may be rather attributed to a coincidence of several developments.
Two frequent challenges6 associated with game data mining are that it is
- complex and requires sufficient expertise and skill, and
- that communicating the results so that they are easily understood and acted upon is not always straightforward but at the same time essential.
These two are, however, not specific to game analytics but rather apply to data analytics in general. Information visualization has been recognized as a powerful tool to assist with the analysis process and can help with analysis, both confirmative and explorative, and presentation7. The aim of confirmatory analysis is to – as the name already implies – the confirm or (or falsify) an a-priori formed hypothesis. Exploratory data analysis (EDA), in contrast, does not seek to answer specific pre-existing hypotheses but rather to discover patterns, trends, or anomalies. EDA can be very useful to develop an initial understanding of the data, to form or refine hypotheses, and to identify new directions for the analysis. As games are complex systems which can give rise to emergent behavior hard to anticipate beforehand, EDA takes on a critical role in game analytics8.
How Visual Analytics can help
Information visualization is beneficial for both approaches as it takes advantage of the cognitive and perceptual abilities of humans9. Indeed, many argue that the analysis process is most effective if automatic analysis techniques are combined with interactive visualizations allowing for more efficient reasoning and decision-making. This integration of the processing and analytical capabilities of computers and humans’ perceptual abilities is an integral part of ‘Visual Analytics’.10
The benefits of both, information visualization and visual analytics, have been recognized early on among game analysts11,12 and form nowadays an indispensable part of game data mining and analytics13. This includes the use and adaption of existing visualization techniques such as heatmaps and node-link diagrams for gameplay analysis. One of the earliest examples of gameplay visualization is the work of Hoobler et al.14 on visualizing player behavior patterns in competitive team games. Since then many visualizations tools and algorithms dedicated to gameplay analysis have been developed. Examples include, DataCracker15 a visual game analytics tool build at Electronic Arts and Ubisoft’s DNA suite16 which offers various visualization and data exploration capabilities.
While the target audience of the aforementioned examples are first and foremost developers, visualizations must not be restricted to developers but can also be specifically targeted towards players13. For instance, a few years ago I proposed an algorithm17 which automatically creates ‘battle maps’ from recorded combat data to give players a means to retrospectively reflect on their performance. In a similar vein, Kuan et al.19 described a visualization system for data from real-time strategy games to help players learn new strategies. Indeed, with more and more games also providing public access to the collected data, the player community has started to use this data to create visualizations on their own.
This is an abbreviated version of my introductory chapter to the book I edited. My full author draft is available here. To cite the chapter: Wallner, G. (2019). A brief overview of data mining and analytics in games. In G. Wallner (Ed.) Data analytics applications in gaming and entertainment, (pp. 1-14). Auerbach Publications. (bibtex)
1 Kantardzic, M. (2011). Data mining: concepts, models, methods, and algorithms. John Wiley & Sons.
2 Coenen, F. (2011). Data mining: past, present and future. The Knowledge Engineering Review, 26(1), 25-29.
3 Zimmerman, E. (2015). Manifesto for a ludic century. In S. P. Walz & S. Deterding (Eds.), The gameful world: Approaches, issues, applications (pp. 19-22). Cambridge, MA: MIT Press.
4 Drachen, A., El-Nasr, M. S., & Canossa, A. (2013). Game analytics–the basics. In Game Analytics (pp. 13-40). Springer, London.
5 Medler, B. (2009). Generations of game analytics, achievements and high scores. Eludamos. Journal for Computer Game Culture, 3(2), 177-194.
6 Powell, R. (2016). Positive and negative effects of game analytics in the game design process: A grounded theory study (Master thesis, Uppsala University).
7 Keim, D. A., Mansmann, F., Schneidewind, J., & Ziegler, H. (2006). Challenges in visual data analysis. In Tenth International Conference on Information Visualization (pp. 9-16). IEEE.
8 Wallner, G., & Kriglstein, S. (2015). An introduction to gameplay data visualization. In P. Lankoski & S. Björk (Eds.), Game research methods (pp. 231-250). ETC Press
9 Fekete, J. D., van Wijk, J. J., Stasko, J. T., & North, C. (2008). The value of information visualization. In Information Visualization (pp. 1-18). Springer, Berlin, Heidelberg.
10 Keim, D., Andrienko, G., Fekete, J. D., Görg, C., Kohlhammer, J., & Melançon, G. (2008). Visual analytics: Definition, process, and challenges. In Information Visualization (pp. 154-175). Springer, Berlin, Heidelberg.
11 Kim, J. H., Gunn, D. V., Schuh, E., Phillips, B., Pagulayan, R. J., & Wixon, D. (2008). Tracking real-time user experience (TRUE): a comprehensive instrumentation solution for complex systems. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems (pp. 443-452). ACM
12 Zoeller, G. (2010). Development telemetry in video games projects. Presentation at the 2010 Game Developer Conference. Retrieved from https://www.gdcvault.com/play/1012227/Development-Telemetry-in-Video-Games
13 Wallner, G., & Kriglstein, S. (2013). ). Visualization-based analysis of gameplay data–a review of literature. Entertainment Computing, 4(3), 143-155.
14 Hoobler, N., Humphreys, G., & Agrawala, M. (2004). Visualizing competitive behaviors in multi-user virtual environments. In Proceedings of the Conference on Visualization’04 (pp. 163-170). IEEE.
15 Medler, B., John, M., & Lane, J. (2011). Data cracker: developing a visual game analytic tool for analyzing online gameplay. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems (pp. 2365-2374). ACM.
16 Dankoff, J. (2014). Game telemetry with DNA tracking on Assassin’s Creed. Retrieved from https://www.gamasutra.com/blogs/JonathanDankoff/20140320/213624/Game_Telemetry_with_DNA_Tracking_on_Assassins_Creed.php
17 Wallner, G. (2018). Automatic generation of battle maps from replay data. Information Visualization, 17(3), 239-256.
18 Kuan, Y. T., Wang, Y. S., & Chuang, J. H. (2017). Visualizing real-time strategy games: The example of StarCraft II. In IEEE Conference on Visual Analytics Science and Technology. IEEE.