Alessandro Canossa

Player modeling using self-organization in Tomb Raider: Underworld

We present a study focused on constructing models of players for the major commercial title Tomb Raider: Underworld (TRU). Emergent self-organizing maps are trained on high-level playing behavior data obtained from 1365 players that completed the TRU game. The unsupervised learning approach utilized reveals four types of players which are analyzed within the context of the game. The proposed approach automates, in part, the traditional user and play testing procedures followed in the game industry since it can inform game developers, in detail, if the players play the game as intended by the game design. Subsequently, player models can assist the tailoring of game mechanics in real-time for the needs of the player type identified.

Game Analytics: Maximizing the Value of Player Data

Developing a successful game in todays market is a challenging endeavor. Thousands of titles are published yearly, all competing for players time and attention. Game analytics has emerged in the past few years as one of the main resources for ensuring game quality, maximizing success, understanding player behavior and enhancing the quality of the player experience. It has led to a paradigm shift in the development and design strategies of digital games, bringing data-driven intelligence practices into the fray for informing decision making at operational, tactical and strategic levels. Game Analytics - Maximizing the Value of Player Data is the first book on the topic of game analytics; the process of discovering and communicating patterns in data towards evaluating and driving action, improving performance and solving problems in game development and game research. Written by over 50 international experts from industry and research, it covers a comprehensive range of topics across more than 30 chapters, providing an in-depth discussion of game analytics and its practical applications. Topics covered include monetization strategies, design of telemetry systems, analytics for iterative production, game data mining and big data in game development, spatial analytics, visualization and reporting of analysis, player behavior analysis, quantitative user testing and game user research. This state-of-the-art volume is an essential source of reference for game developers and researchers. Key takeaways include: Thorough introduction to game analytics; covering analytics applied to data on players, processes and performance throughout the game lifecycle.In-depth coverage and advice on setting up analytics systems and developing good practices for integrating analytics in game-development and -management.Contributions by leading researchers and experienced professionals from the industry, including Ubisoft, Sony, EA, Bioware, Square Enix, THQ, Volition, and PlayableGames. Interviews with experienced industry professionals on how they use analytics to create hit games.

Defining personas in games using metrics

Game metrical data are increasingly being used to enhance game testing and to inform game design. There are different approaches and techniques to gather the metrics data; however there seems to be a lack of frameworks to read and make sense of it. In this paper, the concept of play-persona is applied to game metrics, in the specific case of character-based computer games, where the player controls a single protagonist, around whom the gameplay and -- story evolves. A case is presented for Hitman: Blood Money (IO Interactive, 2007). Player-controlled game characters can be deconstructed into a range of components and these expressed as monitored game metrics. These metrics can subsequently be utilized to discover patterns of play by building play-personas: Modeled representations of how players interact with the game. This process can also be useful to assist game design, by informing whether the game facilitates the specific play patterns implied by theoretical play-personas.

Predicting player behavior in Tomb Raider: Underworld

This paper presents the results of an explorative study on predicting aspects of playing behavior for the major commercial title Tomb Raider: Underworld (TRU). Various supervised learning algorithms are trained on a large-scale set of in-game player behavior data, to predict when a player will stop playing the TRU game and, if the player completes the game, how long will it take to do so. Results reveal that linear regression models and other non-linear classification techniques perform well on the tasks and that decision tree learning induces small yet well-performing and informative trees. Moderate performance is achieved from the prediction models, which indicates the complexity of predicting player behavior based on a constrained set of gameplay metrics and the noise existent in the dataset examined, a generic problem in large-scale data collection from millions of remote clients.

Towards gameplay analysis via gameplay metrics

User-oriented research in the game industry is undergoing a change from relying on informal user-testing methods adapted directly from productivity software development to integrating modern approaches to usability- and user experience testing. Gameplay metrics analysis form one of these techniques, being based on instrumentation methods in HCI. Gameplay metrics are instrumentation data about the user behavior and user-game interaction, and can be collected during testing, production and the live period of the lifetime of a digital game. The use of instrumentation data is relatively new to commercial game development, and remains a relatively unexplored method of user research. In this paper, the focus is on utilizing game metrics for informing the analysis of gameplay during commercial game production as well as in research contexts. A series of case studies are presented, focusing on the major commercial game titles Kane & Lynch and Fragile Alliance.

How players lose interest in playing a game: An empirical study based on distributions of total playing times

Analyzing telemetry data of player behavior in computer games is a topic of increasing interest for industry and research, alike. When applied to game telemetry data, pattern recognition and statistical analysis provide valuable business intelligence tools for game development. An important problem in this area is to characterize how player engagement in a game evolves over time. Reliable models are of pivotal interest since they allow for assessing the long-term success of game products and can provide estimates of how long players may be expected to keep actively playing a game. In this paper, we introduce methods from random process theory into game data mining in order to draw inferences about player engagement. Given large samples (over 250,000 players) of behavioral telemetry data from five different action-adventure and shooter games, we extract information as to how long individual players have played these games and apply techniques from lifetime analysis to identify common patterns. In all five cases, we find that the Weibull distribution gives a good account of the statistics of total playing times. This implies that an average players interest in playing one of the games considered evolves according to a non-homogeneous Poisson process. Therefore, given data on the initial playtime behavior of the players of a game, it becomes possible to predict when they stop playing.

Analyzing spatial user behavior in computer games using geographic information systems

An important aspect of the production of digital games is user-oriented testing. A central problem facing practitioners is however the increasing complexity of user-game interaction in modern games, which places challenges on the evaluation of interaction using traditional user-oriented approaches. Gameplay metrics are instrumentation data which detail user behavior within the virtual environment of digital games, forming accurate and detailed datasets about user behavior that supplement existing user-testing methods such as playtesting and usability testing. In this paper existing work on gameplay metrics is reviewed, and spatial analysis of gameplay metrics introduced as a new approach in the toolbox of user-experience testing and research. Furthermore, Geographic Information Systems (GIS) are introduced as a tool for performing spatial analysis. A case study is presented with Tomb Raider: Underworld, showcasing the merger of GIS with gameplay metrics analysis and its application to game testing and design.

Evaluating motion: spatial user behaviour in virtual environments

User-behaviour analysis has only recently been adapted to the context of the virtual world domain and remains limited in its application. Behaviour analysis is based on instrumentation data, automated, detailed, quantitative information about user behaviour within the virtual environment (VE) of digital games. A key advantage of the method in comparison with existing user-research methods, such as usability- and playability-testing is that it permits very large sample sizes. Furthermore, games are in the vast majority of cases based on spatial, VEs within which the players operate and through which they experience the games. Therefore, spatial behaviour analyses are useful to game research and design. In this paper, spatial analysis methods are introduced and arguments posed for their use in user-behaviour analysis. Case studies involving data from thousands of players are used to exemplify the application of instrumentation data to the analysis of spatial patterns of user behaviour.

Arrrgghh!!!: blending quantitative and qualitative methods to detect player frustration

Frustration, in small, calibrated doses, can be integral to an enjoyable game experience, but it is a very delicate balance: just a slightly excessive amount of frustration could compel players to terminate prematurely the experience. Another factor with high relevance when analyzing player frustration is the difference in personality between players: some are less willing to endure frustration and might give up on the game earlier than others. This article seeks to identify patterns of behavior that could point to potential frustration before players resolve to quit a game. The method should be applicable independently from the personalities of different players. Furthermore, in order for this method to be relevant during game production, it has been decided to avoid relying on large numbers of players, and instead depend on highly granular data and both qualitative approaches (direct observation of players) and quantitative research (data mining gameplay metrics). The result is a computational model of player frustration that, although applied to a single game (Kane & Lynch 2), is able to raise a red flag whenever a sequence of actions in the game could be interpreted as possible player frustration.

Game Analytics – The Basics

Developing a profitable game in today’s market is a challenging endeavor. Thousands of commercial titles are published yearly, across a number of hardware platforms and distribution channels, all competing for players’ time and attention, and the game industry is decidedly competitive. In order to effectively develop games, a variety of tools and techniques from e.g. business practices, project management to user testing have been developed in the game industry, or adopted and adapted from other IT sectors. One of these methods is analytics, which in recent years has decidedly impacted on the game industry and game research environment.