Alessandro Canossa

Royal Danish Academy of Fine Arts, Schools of Architecture, Design and Conservation · School of Design

The objective of this paper is to explore potential associations between development teams and the characteristics of the games they produce. Through a production study of Danish game companies and a design analysis of their games, we propose that there are statistically significant associations between features of the game and the team that produc...

This paper explores how games can facilitate greater autonomous experiences. The project describes possibilities of how a certain kind of simulation can be a viable substitute for the often overwhelming and explicit communications of information that characterize many instances of handholding in video games. We hypothesize that consistently support...

The rapidly growing field of text-to-image generation leverages machine learning and natural language processing to allow for the creation of very diverse and high-quality images. Whilst these images can be used in various forms and for many purposes, this paper addresses a specific question: The possibility of utilizing text-to-image generators to...

When attempting to understand a phenomenon or learn new concepts, we often use data to create models of reality, but “the map is not the territory”. We treat these imperfect abstractions as the reality itself, we design standardized dashboards to account for the multidimensional interdependencies of systems, each already complex in its own right. I...

What strategies, company organisations, and design decisions render video game titles successful and secure the survivability of a game development studio? These are important questions, subject to situational and contextual variation. Nevertheless, different approaches clearly make a major impact on the public reception or economical outcome of a...

Serious games (or transformational games) are used to operate transformations on players that range from transferring knowledge to changing players’ sense of self. Since these games have other purposes besides entertainment, it is necessary to validate them with a whole new set of methods other than the parameters utilized for traditional software...

This chapter discusses different clustering methods and their application to game data. In particular, the chapter details K-means, Fuzzy C-Means, Hierarchical Clustering, Archetypical Analysis, and Model-based clustering techniques. It discusses the disadvantages and advantages of the different methods and discusses when you may use one method vs....

This chapter introduces the basics of statistics and probability theory that will be used throughout the book. Specifically, it introduces the concepts behind descriptive statistics, including aspects of using visualization of means, medians, and modes, as well as distribution visualizations to understand your data for further analysis. It also int...

This book is aimed at giving readers an introduction to the practical side of game data science and thus can be used a textbook for game analytics or game user research class or as a reference to self learners and enthusiasts. Game data science is a term that we use to denote a process composed of methods and techniques by which an analyst or a dat...

This chapter discusses Social Network Analysis, a technique used to analyze social networks within social games as a method to enhance retention in games. We will show how one can use this method by applying it to the problem of retention within the game Tom Clancy’s The Division ( TCTD ). Using the game and the analysis will help you understand ho...

This chapter introduces the techniques used to abstract the data from low-level data to features that can be used to visualize and develop models to inform the different stakeholders. These techniques range from (a) knowledge engineering, where expert knowledge is used to develop formulae to compute various measures from low-level data; (b) feature...

This chapter discusses more advanced methods for sequence analysis. These include: probabilistic methods using classical planning, Bayesian Networks (BN), Dynamic Bayesian Networks (DBNs), Hidden Markov Models (HMMs), Markov Logic Networks (MLNs), Markov Decision Process (MDP), and Recurrent Neural Networks (RNNs), specifically concentrating on LST...

This chapter focuses on the process of cleaning data and preparing it for further processing. Specifically, the chapter discusses various techniques that you will use, including preprocessing, outlier identification, data consistency, and the normalization or standardization process, used to normalize your data. The chapter further discusses differ...

This chapter introduces the topic of this book: Game Data Science. Game data science is the process of developing data-driven techniques and evidence to support decision-making across operational, tactical, and strategic levels of game development, and this is why it is so valuable. This chapter introduces this topic as well as outlines the process...

This chapter will introduce the use of Neural Networks (NN) in game data science. Due to the availability of game data and the increase in computational power, the use of NNs and deep networks is on the rise in data science in general, and specifically within the field of game data science. Complex deep networks are used as they can generalize to h...

This chapter discusses several classification and regression methods that can be used with game data. Specifically, we will discuss regression methods , including Linear Regression , and classification methods, including K-Nearest Neighbor, Naïve Bayes, Logistic Regression, Linear Discriminant Analysis, Support Vector Machines, Decisions Trees , an...

This chapter discusses the topic of how one can use visualization techniques to analyze game data. Specifically, the chapter delves into the development of heatmaps to analyze spatio-temporal data. The chapter also discusses spatio-temporal visualizations and state-action transition visualizations. We also discuss two visualization systems that we...

This chapter focuses on two specific steps in the machine learning process, called model validation and model evaluation. Specifically, model validation is the step used to tune the hyperparameters of the model. Here, we often integrate a cross-validation process, which we discuss in detail in this chapter. Model evaluation, on the other hand, is t...

This chapter is devoted to sequence game data analysis. It will first define what sequence data is and how it is represented, and then delve more deeply into how to develop models from such data. Sequence analysis has a lot of utility and is important as it conserves the sequence of player actions and can shed light on how players solved different...

This chapter summarizes the takeaways from the different chapters of this book on the game data science process we introduced in Chapter 1. It shares some notes and experiences that can help you when embarking on using the methods discussed in this book. As a conclusion chapter, it will also delve into important topics that are not discussed in oth...

This book is aimed at giving readers an introduction to the practical side of game data science and thus can be used a textbook for game analytics or game user research class or as a reference to self learners and enthusiasts. Game data science is a term that we use to denote a process composed of methods and techniques by which an analyst or a dat...

Is it possible to detect toxicity in games just by observing in-game behavior? If so, what are the behavioral factors that will help machine learning to discover the unknown relationship between gameplay and toxic behavior? In this initial study, we examine whether it is possible to predict toxicity in the MOBA gameFor Honor by observing in-game be...

Understanding player strategies is a key question when analyzing player behavior both for academic researchers and industry practitioners. For game designers and game user researchers, it is important to gauge the distance between intended strategies and emergent strategies; this comparison allows identification of glitches or undesirable behaviors...

There has been much work on player modeling using game behavioral data collected. Many of the previous research projects that targeted this goal used aggregate game statistics as features to develop behavior models using both statistical and machine learning techniques. While existing methods have already led to interesting findings, we suspect tha...

In a wide range of social networks, people's behavior is influenced by social contagion: we do what our network does. Networks often feature particularly influential individuals, commonly called "influencers." Existing work suggests that in-game social networks in online games are similar to real-life social networks in many respects. However, we d...

Is it possible to predict the motivation of players just by observing their gameplay data? Even if so, how should we measure motivation in the first place? To address the above questions, on the one end, we collect a large dataset of gameplay data from players of the popular game Tom Clancy's The Division (Ubisoft, 2016). On the other end we ask th...

In a wide range of social networks, people’s behavior is influenced by social contagion: we do what our network does. Networks often feature particularly influential individuals, commonly called “influencers’.’ Existing work suggests that in-game social networks in online games are similar to reallife social networks in many respects. However, we d...

In this paper we present an approach to using sequence analysis to model player behavior. This approach is designed to work in game development contexts, integrating production teams and delivering profiles that inform game design. We demonstrate the method via a case study of the game Tom Clancy’s The Division, which with its 20 million players re...

In order to appeal to a growing market, game developers are offering a wide variety of activities. It is becoming necessary to understand which psychological need each activity caters for. The purpose of this paper is to demonstrate the development and evaluation of an instrument to assess which basic psychological needs are satisfied by different...

During the last decade, game developers and researchers have started to extensively collect in-game data of players in order to guide decision-making. This has led to the emergence of the new field of game analytics, that is, data analytics in the context of games.1 Over the last years, game analytics has considerably contributed to our understandi...

Player modeling is an important concept that has gained much attention in game research due to its utility in developing adaptive techniques to target better designs for engagement and retention. Previous work has explored modeling individual differences using machine learning algorithms per- formed on aggregated game actions. However, players' ind...

Within Entertainment Computing, games research has grown to be its own area, with numerous publication venues dedicated to it. As this area evolves, it is fruitful to examine its overall development—which subcommunities and research interests were present from the start, which have come and gone, and which are currently active—to better understand...

In this paper we present an approach for using sequence analysis to model player behavior. This approach is designed to work in game development contexts, integrating production teams and delivering profiles that inform game design. We demonstrate the method via a case study of the game Tom Clancy’s The Division, which with its 20 million players r...

Understanding player behavior and making sense of gameplay actions is a non-trivial and time-consuming process that requires both thorough domain knowledge of game design, and advanced technical skills in database query languages and statistical packages. Researchers, technology partners and content creators are developing tools to aid in the proce...

In the real world, coupled eye and head movements are used by humans and other animals to orient their gaze toward objects or scenes of interest. In virtual environments a mouse is often used as a proxy for head movements, orienting the camera towards a desired view direction. The mouse also controls body direction during navigation, orienting the...

In both industry and academia, software tools are essential for games user research (GUR) in order to collect, integrate, analyze and report on games and players' data. GUR datasets are becoming more and more complex, detailed and multifaceted. Hence, tools are necessary to efficiently handle data. This one-day workshop explores the vast spectrum o...

In this paper we present an analysis of the academic landscape of games research from the last 15 years. We employed a data driven approach utilizing co-word and co-venue analysis on 48 core venues to identify 20 major research themes and 7 distinct communities, with a total of 8,207 articles and 21,552 unique keywords being analyzed. Strategic dia...

From social sciences to biology and physics, gamified systems and games are increasingly being used as contexts and tools for research: as “petri dishes” for observing macro-social and economic dynamics; as sources of “big” and/or ecologically valid user behavior and health data; as crowdsourcing tools for research tasks; or as a means to motivate...

A Northeastern University research project studying the effects of perceived gender on League of Legends player behavior via Riot's official API.

There has been an increasing interest in the debate on the value and relevance using video games for learning. Some of the interest stems from frustration with current educational methods. However, some of this interest also stems from the observations of large numbers of children that play video games. This paper finds that children can learn basi...

There has been an active debate on the value and relevance of the use of video games for learning. Some of this interest stems from frustration with current educational tools. Some of this interest stems from observations of large numbers of people that play video It uses a method for evaluating indicators of cognition that take place within a comm...

Understanding player behavior through telemetry logs is an important yet unresolved problem. Interpreting the meaning of players' low-level behaviors over time is important due to its utility in (a) developing a more adaptive and personalized game experience, (b) uncovering game design issues, and (c) understanding the human cognitive processes in...

There is an undeniable growing trend among players towards unconditional acceptance of behavior tracking in digital gamesThis trend has muted one of the two interlocutors necessary for a transcendent Hegelian dialectic that finds a viable synthesis between a corporate thesis that attempts to gather more and more data aimed at maximizing profit, and...

During the past few years there has been an explosion on the number of games that are used for learning. Recently, there has been an emphasis on determining what players learn when they play a game, how they problem solve or make decisions and how such decisions progress through time showing some aspect of learning. This paper focuses on uncovering...

Behavioral datasets from major commercial game titles of the “AAA” grade generally feature high dimensionality and large sample sizes, from tens of thousands to millions, covering time scales stretching into several years of real-time, and evolving user populations. This makes dimensionality-reduction methods such as clustering and classification u...

Recently both game industry professionals and academic researchers have started focusing on player-generated behavioral data as a mean to gather insights on player psychology through datamining. Although some research has already proven solid correlations between in-game behavior and personality, most techniques focus on extracting knowledge from i...

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 compa...

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 novel techniques, being based on instrumentation methods in H...

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 t...

Unity 3D is an integrated authoring tool for creating 3D interactive environments, such as games and real-time 3D visualizations. Unity consists of both an editor, for designing content, and a game engine, for executing the final product. Over the recent years since its inception in 2006, Unity was given several awards, including Wall Street Journa...

The process of creating a game is a perfect example of a multidisciplinary effort. Development teams are extremely heterogeneous, involving writers, programmers, artists, designers, engineers and architects, just to name a few. Each discipline brings a legacy of assumptions, practices and values that, more often than not, are far from aligned with...

Games User Research (GUR) has gained a lot of ground recently in game development. It has become apparent just how beneficial knowing your target audience really is. More and more, studios and publishers integrate user-oriented methods in their development process and report direct benefits from this practice, above and beyond simple focus group fe...

Digital Chocolate is a development studio focused on social and casual games for PCs, smartphones and consoles. The firm was founded in 2003 by Trip Hawkins; since then it has won more than ten awards including “Best Game Developer of the Year” award from both IGN and Mobile Entertainment. The most successful games developed are free to play and in...

Kiloo is a game and apps development studio based in Denmark, focusing exclusively on mobile phones and has been doing so since 2000 when phones displays had double digit resolutions and two colors, and games could fit in 30 Kb. The company was started by Jacob Møller. In 2008, with the explosion of smartphones, it skyrocketed from 14 to 45 employe...

Serious Games Interactive (SGI) started in 2006 as a research spinoff. The company was founded in cooperation with Unity Technologies as a technology provider with the ambition of making the world’s best serious games by harnessing the potential and design principles of real AAA titles. The company received considerable critical praise both from ed...

Nicklas Nygren is an archetypal independent game developer working in Sweden and Denmark, mostly alone or in very small teams, and specializes in side-scrolling, two-dimensional adventure platformers for desktop computers. He never planned to become a game developer or dreamed to work in a big studio, Nicklas just wanted to make cool games, mostly...

Every day Zynga, the social gaming company behind hits such as Zynga Poker, FarmVille and Words with Friends, runs extensive statistical analysis of reams of data. Zynga has one of the largest data warehouses in the world, and the company needs it; its games generate over 15 terabytes of new data daily.

Junebud, is a game development studio employing around 20 people and focused on digitally distributed, low threshold MMOs both for browsers and mobile phones. Junebud’s business model revolves around digital distribution and free-to-play games, a couple of examples are: Milmo (Aeria Games, 2011) a browser game that blends 3D platform gaming with Ac...

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 telemet...

Game Analytics has gained a tremendous amount of attention in game development and game research in recent years. The widespread adoption of data-driven business intelligence practices at operational, tactical and strategic levels in the game industry, combined with the integration of quantitative measures in user-oriented game research, has caused...

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 engagem...

We describe an approach to using standard data mining algorithms to help analyse recurring themes in game design across several games, and to help suggest novel game design ideas. This is illustrated with the analysis of 119 different resource systems across 20 games. Clustering is used to validate the assignment of resources into archetypes; frequ...

Understanding how personality, motives, values, goals and belief systems affect the behavior of players is crucial for designers of digital games. Whether the goal is pure entertainment, education or behavior change, knowing what makes different people tick means understanding the reasons for their behavior. This understanding allows the creation o...

User research in digital game development has in recent years begun to expand from a previous existence on the sideline of development, to a central factor in game production, in recognition that the interaction between user and game is crucial to the perceived user experience. Paralleling this development, the methods and tools available for condu...

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 playe...

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...

In recent years, the gaming industry has grown up and digital games have become more complex products. With this maturity comes an increasing need for formal playtesting methods from user research and scientific methods from academia. Employing user research methods in game development, especially combined qualitative (e.g., questionnaires, intervi...

What is exactly level design? It is juggling 12 balls in the air at the same time, it is solving differential equations with 12 variables, it is trying to realize a vision when everybody is tearing at it. Artists, programmers, marketing PRs, scripters, designers. People from very different backgrounds and with even more varying motivations converge...

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...

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 de...