Feature analysis for modeling game content quality

2009

This paper investigates the relationship between level design parameters of platform games, individual playing characteristics and player experience. The investigated design parameters relate to the placement and sizes of gaps in the level and the existence of direction changes; components of player experience include fun, frustration and challenge. A neural network model that maps between level design parameters, playing behavior characteristics and player reported emotions is trained using evolutionary preference learning and data from 480 platform game sessions. Results show that challenge and frustration can be predicted with a high accuracy (77.77% and 88.66% respectively) via a simple single-neuron model whereas model accuracy for fun (69.18%) suggests the use of more complex non-linear approximators for this emotion. The paper concludes with a discussion on how the obtained models can be utilized to automatically generate game levels which will enhance player experience.

2015 7th International Conference on Games and Virtual Worlds for Serious Applications (VS-Games), 2015

This paper presents a novel approach to evaluate game level design strategies, applied to role playing games. Following a set of well defined guidelines, two game levels were designed for Neverwinter Nights 2 to manipulate particular emotions like boredom or flow, and tested by 13 subjects wearing a brain computer interface helmet. A set of features was extracted from the affective data logs and used to classify different parts of the gaming sessions, to verify the correspondence of the original level aims and the effective results on people emotions. The very interesting correlations observed, suggest that the technique is extensible to other similar evaluation tasks.

In this paper, we describe a methodology for capturing player experience while interacting with a game and we present a data-driven approach for modeling this interaction. We believe the best way to adapt games to a specific player is to use quantitative models of player experience derived from the in-game interaction. Therefore, we rely on crowd-sourced data collected about game context, players behavior and players self-reports of different affective states. Based on this information, we construct estimators of player experience using neuroevolutionary preference learning. We present the experimental setup and the results obtained from a recent case study where accurate estimators were constructed based on information collected from players playing a firstperson shooter game. The framework presented is part of a bigger picture where the generated models are utilized to tailor content generation to particular player's needs and playing characteristics.

The Visual Computer, 2016

Game science has become a research field which attracts industry attention due to a worldwide rich sell-market. In order to understand the player experience, concepts like Flow or Boredom mental states require formalization and empirical investigation, taking advantage of the objective data that psychophysiological methods like electroencephalography (EEG) can provide. This work studies the affective ludology and shows two different game levels for Neverwinter Nights 2 developed with the aim to manipulate emotions; two sets of affective design guidelines are presented, with a rigorous formalization that considers the characteristics of Role-Playing genre and its specific gameplay. An empirical investigation with a brain-computer interface headset has been conducted: by extracting numerical data features, machine learning techniques classify the different activities of the gaming sessions (task and events) to verify if their design differentiation coincides with the affective one. The observed results, also supported by subjective questionnaires data, confirm the goodness of the proposed guidelines suggesting that this evaluation methodology could be extended to other evaluation tasks.

Cmc-computers Materials & Continua, 2021

Game player modeling is a paradigm of computational models to exploit players’ behavior and experience using game and player analytics. Player modeling refers to descriptions of players based on frameworks of data derived from the interaction of a player’s behavior within the game as well as the player’s experience with the game. Player behavior focuses on dynamic and static information gathered at the time of gameplay. Player experience concerns the association of the human player during gameplay, which is based on cognitive and affective physiological measurements collected from sensors mounted on the player’s body or in the player’s surroundings. In this paper, player experience modeling is studied based on the board puzzle game “Candy Crush Saga” using cognitive data of players accessed by physiological and peripheral devices. Long Short-Term Memory-based Deep Neural Network (LSTM-DNN) is used to predict players’ effective states in terms of valence, arousal, dominance, and liki...

Applications of Evolutionary …, 2012

A recent trend within computational intelligence and games research is to investigate how to affect video game players' in-game experience by designing and/or modifying aspects of game content. Analysing the relationship between game content, player behaviour and self-reported affective states constitutes an important step towards understanding game experience and constructing effective game adaptation mechanisms. This papers reports on further refinement of a method to understand this relationship by analysing data collected from players, building models that predict player experience and analysing what features of game and player data predict player affect best. We analyse data from players playing 780 pairs of short game sessions of the platform game Super Mario Bros, investigate the impact of the session size and what part of the level that has the major affect on player experience. Several types of features are explored, including item frequencies and patterns extracted through frequent sequence mining.

HAL (Le Centre pour la Communication Scientifique Directe), 2022

This paper describes an automated evaluation of the overall game experience using a synthetic agent, that we contextualize for First-Person Shooter games. This evaluation method is based on the characterization of the game experience through dynamics of major FPS games. We define dynamics as sequences of events that are meaningful for the player during the game session. As they trigger players' emotional responses, and influence their overall enjoyment and motivation, we classify them according to Motives for Play like curiosity, thrill-seeking, problem-solving, victory, and acquisition, in order to facilitate the evaluation process. Based on that, our evaluation method proposes to select synthetic agent routines that target a distinct game experience while playing a game session, using a selection of game dynamics. As the agent navigates through the level and interacts with opponents, dynamics may occur and, if so, are automatically identified, and then classified as Motives for Play. In the end, this classification can be used to evaluate the game experience and the quality of the level itself during playtesting sessions. It may also be utilized to assist the procedural generation of any level that target a specific game experience. CCS Concepts: • Human-centered computing → User models; • Applied computing → Computer games; Psychology.

We report research on player modeling using psychophysiology and machine learning, conducted through interdisciplinary collaboration between researchers of computer science, psychology, and game design at Aalto University, Helsinki. First, we propose the Play Patterns And eXperience (PPAX) framework to connect three levels of game experience that previously had remained largely unconnected: game design patterns, the interplay of game context with player personality or tendencies, and state-of-the-art measures of experience (both subjective and non-subjective). Second, we describe our methodology for using machine learning to categorize game events to reveal corresponding patterns, culminating in an example experiment. We discuss the relation between automatically detected event clusters and game design patterns, and provide indications on how to incorporate personality profiles of players in the analysis. This novel interdisciplinary collaboration combines basic psychophysiology research with game design patterns and machine learning, and generates new knowledge about the interplay between game experience and design.

With computers becoming ubiquitous and high resolution graphics reaching the next level, computer games have become a major source of entertainment. It has been a tedious task for game developers to measure the entertainment value of the computer games. The entertainment value of a game does depend upon the genre of the game in addition to the game contents. In this paper, we propose a set of entertainment metrics for the platform genre of games. The set of entertainment metrics is proposed based upon certain theories on entertainment in computer games. To test the metrics, we use an evolutionary algorithm for automated generation of game rules which are entertaining. The proposed approach starts with an initial set of randomly generated games and, based upon the proposed metrics as an objective function, guides the evolutionary process. The results produced are counterchecked against the entertainment criteria of humans by conducting a human user survey and a controller learning ability experiment. The proposed metrics and the evolutionary process of generating games can be employed by any platform game for the purpose of automatic generation of interesting games provided an initial search space is given.

2011

This paper presents a methodology which allows for an objective analysis of video game quality based on player behaviour. A mutually exclusive and exhaustive code of 5 behavioural states is presented based on an analysis of 10 users each playing 3 video games. The coding scheme is verified for inter-coder agreement with resulting Kappa values in the range of 0.74 to 0.91 (good agreement to very good agreement). Results of the game studies presented show that good games allow the player to enter the Engagement state more frequently, and keep them in that state for a longer duration than bad games. In particular, the results show that good games exhibit an overall net positive behaviour from the very early stages of gameplay. The paper concludes with suggestions for future work.