There is a popular story about technology in which virtual objects and virtual reality are, or will soon become, “digital twins” of the regular world. In this story, a virtual experience possesses (or will possess) all the details of what it represents, making virtual reality “transparent,” with no need to design or learn new interfaces. This story is propagated not only by technology companies but also by designers seeking perfect immersion and presence, and by what we term “Matrix philosophy”: a focus on hypothetical future technologies, such as seen in movies, at the expense of existing technologies and experiences.

Figure 1: Clusters of countries with similar cultural attitudes based on two different sets of metrics and algorithms.1a (left) uses mean values and hierarchical clustering.1b (right) uses cosine similarity and k-means clustering.

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 behavior for players that have been labeled as toxic (i.e. players that have been sanctioned by Ubisoft community managers). We test our hypothesis of detecting toxicity through gameplay with a dataset of almost 1,800 sanctioned players, and comparing these sanctioned players with unsanctioned players. Sanctioned players are defined by their toxic action type (offensive behavior vs. unfair advantage) and degree of severity (warned vs. banned). Our findings, based on supervised learning with random forests, suggest that it is not only possible to behaviorally distinguish sanctioned from unsanctioned players based on selected features of gameplay; it is also possible to predict both the sanction severity (warned vs. banned) and the sanction type (offensive behavior vs. unfair advantage). In particular, all random forest models predict toxicity, its severity, and type, with an accuracy of at least 82%, on average, on unseen players. This research shows that observing in-game behavior can support the work of community managers in moderating and possibly containing the burden of toxic behavior.

Intimate controllers are defined as devices that require players to breach their comfort zone and interpersonal boundaries to establish a physical contact between players. We developed a game that requires players to hold each other's hands to perform a special action. The main purpose was to investigate the impact that this alternative controller has on player experience. Two version of the game were created: with and without intimate controllers. We had two groups playing with each version and then fill a survey to evaluate player experience. Player experience was assessed using the Game Experience Questionnaire (Core Module, Social Presence Module and Post-game Module) but given some serious concerns regarding this model, we analyzed the data bypassing the factors and instead focusing on individual answers. The data shows that intimate controllers can lead to a much more engaging experience and feelings of closeness to other players, while eliciting stronger emotions, both positive and negative. There are also unexpected results in terms of increased engagement with the narrative aspect of the game while also reporting a decreased feeling of mastery and skills and increased weariness.

We present a game designed with the specific purpose of transferring non-trivial knowledge about sustainable food production and consumption practices. The game simulation has been designed as an interactive infographic with a double impact: besides the obvious purpose of knowledge transfer we also wanted to provide users with a visceral visualization that at a glance can capture in detail the state of the system so it can represent the consequences of each player choice. This visualization tries to be aligned with the tenets of data humanism, "ready to question the impersonality of a merely technical approach to data and to begin designing ways to connect numbers to what they really stand for: knowledge, behaviors, people"[10].

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 do not know whether there are in-game equivalents to influencers. We therefore applied standard social network features used to identify influencers to the online multiplayer shooter Tom Clancy's The Division. Results show that network feature-defined influencers had indeed an outsized impact on playtime and social play of players joining their in-game network.

There has been considerable interest in measuring cognitive load . While researchers use retrospective think aloud methods to gauge an individuals cognitive load, others have expressed concerns about the reliability of think aloud methods. Moreover, others have expressed concerns about the reliability of using think-aloud methods with young children. This article provides evidence of non-invasive psycho-physiological tools that can be used to measure the cognitive load of young children. The authors employ eye-tracking technology to measure the players cognitive load through changes in endogenous blinks and fixations. Our process finds significant changes in cognitive load between childrens first and second attempts at playing puzzle-based computer games. The results of the study provide game developers with tools that indicate when users struggle with the information or content in a computer game.

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. On the other end, we ask them to report their levels of competence, autonomy, relatedness and presence using the Ubisoft Perceived Experience Questionnaire. After processing the survey responses in an ordinal fashion we employ preference learning methods based on support vector machines to infer the mapping between gameplay and the reported four motivation factors. Our key findings suggest that gameplay features are strong predictors of player motivation as the best obtained models reach accuracies of near certainty, from 92% up to 94% on unseen players.

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 video games. This work is part of a growing effort in HCI to develop surveys able to capture subtle nuances of the player experience. This model, UPEQ, was developed by transforming a self-determination theory questionnaire into a video game specific survey. UPEQ consists of three subscale of Autonomy, Competence and Relatedness, which, through two studies focusing on development and validation of the model showed significant correlations with other self-reported measures of sense of transportation to the game as well as enjoyment of and engagement with the game. Regression with in-game behavior of players tracked by game engine also confirmed that each subscale of UPEQ independently predicts playtime, money spent on the game and playing as a group.

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 of more efficient content since it means acknowledging the individual differences that define every human being. A deeper understanding of players' personality from play behavior is very relevant also for adaptive systems aimed at increasing level of immersion. Indeed, knowing more about players' personality could help design systems more responsive to players' desires and goals increasing the potential benefits of serious application of digital games. The behavior of Minecraft players is analyzed through the lens of User-Initiated Events (UIE) logged by the game system and related to the 16 basic desires enunciated by Reiss in his analysis of motivation.

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.