Player Modeling

In the context of video games, dynamic difficulty adjustment (DDA) offers a dynamic solution to match the in-game difficulty to the player's needs. In this study, we aimed to assess the added value of pupillometry features in the context of DDA and player experience modeling to predict experienced difficulty. A user study was conducted, during which participants played nine rounds of Pac-Man at different difficulties and for which gameplay-, game context-and pupillometry data were gathered together with participants' responses regarding game experience. Multiple random forest classifiers were trained on different feature subsets, with and without pupillometry features, to predict experienced difficulty. We found that the addition of pupillometry features did not lead to a performance improvement of the classifiers. This finding was supported by the results of our data analysis; only for the distributions of two of the four pupillometry features significant differences were found for the lowest and some of the other levels of self-reported experienced challenge. No convincing inverted u-curve was found to describe the relation between pupil size and experienced difficulty. A cautious inverted u-curve was found for pupil size with respect to the ingame difficulty. Based on our results we question whether pupillometry, as objective measure, is informative in the prediction of the subjective perception of difficulty. We propose future directions with respect to pupillometry features, the prediction of experienced difficulty and the prediction of the optimal load, together with a follow up study for which the constructed dataset can be reused.

Player modeling is a crucial procedure for the user-oriented videogame design. For player modeling to be achieved, modeling domain knowledge is essential. Mastering the semantics of a domain is to learn the "language" of the domain. In the present study, two approaches to representing "words" are considered and analyzed comparatively. The first approach ("grid" representation) is based on the division of the game terrain as a grid, capturing in each cell the content-based information of the action game. The second approach ("holistic" representation) captures the contextual information in which the action takes place (life, score, shield, number of hit asteroids etc.). For the present comparative analysis, we use the action videogame SpaceDebris. We analyze the data using the classification algorithms J48, Naive Bayes, and SMO, as well as the Kmeans clustering and we compare the results in an attempt to identify the approach that represents the semantic space more reliably. The data acquired from the"grid" representation perform better, however the low value of the performance's difference does not allow us to come to rock solid conclusions.

A growing research community is working toward employing drama management components in story‐based games. These components gently guide the story toward a narrative arc that improves the player's gaming experience. In this article we evaluate a novel drama management approach deployed in an interactive fiction game called Anchorhead. This approach uses player's feedback as the basis for guiding the personalization of the interaction. The results indicate that adding our Case‐based Drama manaGer (C‐DraGer) to the game guides the players through the interaction and provides a better overall player experience. Unlike previous approaches to drama management, this article focuses on exhibiting the success of our approach by evaluating results using human players in a real game implementation. Based on this work, we report several insights on drama management which were possible only due to an evaluation with real players.

Gameplay in single-player shooter games primarily consists of combat with Non-player Characters (NPCs). However, there has been little research done to study how enemy NPCs affect player behavior in shooter games. As a consequence, there is no formal language for designers to discuss how NPCs are used in shooter games. This paper presents design patterns for NPCs in shooter games and explores their effects on gameplay. These patterns help designers communicate about and explore new ideas for enemy NPCs and further our understanding about how NPC types can be implemented, enabling more engaging experiences.

Predicting and improving player retention is crucial to the success of mobile Free-to-Play games. This paper explores the problem of rapid retention prediction in this context. Heuristic modeling approaches are introduced as a way of building simple rules for predicting short-term retention. Compared to common classification algorithms, our heuristic-based approach achieves reasonable and comparable performance using information from the first session, day, and week of player activity.

With games continuously and rapidly evolving to become more complex and sophisticated in their nature and implementation. There is a fundamental need to sustain and deliver a similarly advanced, realistic, and engaging experience for the player. The implementation of “emergence” within games as providing an effective means to sustain this engagement in conjunction with some form of action recognition mechanism for its support. More recently, games have made much of the “adaptive” mechanisms that tailor the player experience during the game, but much of this appears to be implemented by merely making the game harder according to the success of the player. Some go further than this by incorporating adaptive AI that change agent tactics to suit the player's style of play. Whilst these are clearly advances in the approach to providing a player-centric experience to engage the player, the basis and transferability of these approaches is open to question. Here we propose a limited fla...

Digital games are dynamic environments where the players interact with the games and, commonly, also with other players. The players' interactions have many types of relationships, both with other players (e.g., be friend, share games) and with games (e.g., buy, play, like); these relationships can be represented by social networks, i.e., in this context, a Social Network of Games (SNG). During a gameplay, the player produces a vast amount of data continuously: data that represents his/her experiences, preferences and behavioral patterns. In this way, it is possible to use these data to understand the players' preferences, i.e., Player Modeling, and to improve the attractiveness of new games. However, this task requires the analysis of a vast amount of data, what is impracticable to do manually, then requiring robust algorithms of a research area named Knowledge Discovery in Databases (KDD) to overcome such an issue. It is possible to apply KDD techniques in data of a SNG to model the players, as well as to identify intrinsic features of the games. This MSc work aimed to explore a real SNG using KDD techniques for identifying common features among popular games, which may represent reasons why the games are popular. However, to achieve this goal, it is necessary to analyze games developed by non-influencer makers, because influencers may receive biased attention in their games that is not necessarily motivated by the game quality. First, we focused on detecting the game influencers to filter them out; empirical experiments show that our approach automatically detects influencers with high precision, even when using data from distinct nationalities for training and testing. Then, we performed a detailed analysis of games' features, searching for object combinations that occur in the popular games developed by non-influencer makers, so to support game designers in the elaboration process of new games. This case study introduces a new design pattern for platform games. Also, we present an extensive analysis of object combinations that commonly occur in popular games. All experiments were performed on players and games from the worldwide well-known Super Mario Maker (Nintendo, Kyoto, Japan).

There are a wide variety of studies on player modeling. However, most of these studies target a specific game or genre. In some of these works, the number of in-game actions is used as a feature for modeling a player. However, using this feature leads to a complex model, and the model may miss some high-level relations among actions. In this paper, we propose a generic player modeling method that uses actiontrait mapping relations which reveal correlations among actions. Mapping from the action-space to a much smaller traitspace improves interpretability of models. Additionally, to use the differences of impact of actions on player models, we apply feature weighting which uses the inverse of action frequencies. Players are clustered by Expectation Maximization. We demonstrate our method on a casual mobile game, Dusk Racer. We evaluate the feature weighting method using cluster validation with internal criteria. We conclude that using traits and feature weighting improves clustering ...

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 that aggregated features discard valuable information such as temporal or sequential patterns, which are important in deciphering information about decision-making, problem solving, or individual differences. Such sequential information is critical to analyze player behaviors especially in role-playing games (RPG) where players face ample choices, experience different contexts, behave freely with individual propensities but possibly end up with similar aggregated statistics (e.g., levels, time spent). Using an RPG with multiple affordances, we designed an experiment collecting granular in-game behaviors of 64 players. Using closed sequential ...

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 that aggregated features discard valuable information such as temporal or sequential patterns, which are important in deciphering information about decision-making, problem solving, or individual differences. Such sequential information is critical to analyze player behaviors especially in role-playing games (RPG) where players face ample choices, experience different contexts, behave freely with individual propensities but possibly end up with similar aggregated statistics (e.g., levels, time spent). Using an RPG with multiple affordances, we designed an experiment collecting granular in-game behaviors of 64 players. Using closed sequential ...

In this chapter, we explore methods for automatically generating game content — and games themselves — adapted to individual players, in order to improve their playing experience or achieve a desired effect. This goes beyond notions of mere replayability, and involves modelling player needs to maximise their enjoyment, involvement and interest in the game being played. We identify three main aspects of this process: Generation of new content and rule sets; Measurement of this content and the player; Adaptation of the game to change player experience. This process forms a feedback loop of constant refinement, as games are continually improved while being played. Framed within this methodology, we present an overview of our recent and ongoing research in this area. This is illustrated by a number of case studies that demonstrate these ideas in action over a variety of game types, including: 3D action games, arcade games, platformers, board games, puzzles and open world games. We draw ...

Your article is published under the Creative Commons Attribution license which allows users to read, copy, distribute and make derivative works, as long as the author of the original work is cited. You may selfarchive this article on your own website, an institutional repository or funder's repository and make it publicly available immediately.

Designing and developing computer games can be a complex activity that may involve professionals from a variety of disciplines. In this article, we examine the use of game theory for supporting the design of gameplay within the different sections of a computer game and demonstrate its application in practice via adapted high-level decision trees for modeling the flow in gameplay and payoff matrices for modeling skill or challenge levels.

Gameplay in single-player shooter games primarily consists of combat with Non-player Characters (NPCs). However, there has been little research done to study how enemy NPCs affect player behavior in shooter games. As a consequence, there is no formal language for designers to discuss how NPCs are used in shooter games. This paper presents design patterns for NPCs in shooter games and explores their effects on gameplay. These patterns help designers communicate about and explore new ideas for enemy ...

Gameplay in single-player shooter games primarily consists of combat with Non-player Characters (NPCs). However, there has been little research done to study how enemy NPCs affect player behavior in shooter games. As a consequence, there is no formal language for designers to discuss how NPCs are used in shooter games. This paper presents design patterns for NPCs in shooter games and explores their effects on gameplay. These patterns help designers communicate about and explore new ideas for enemy ...

Gameplay in single-player shooter games primarily consists of combat with Non-player Characters (NPCs). However, there has been little research done to study how enemy NPCs affect player behavior in shooter games. As a consequence, there is no formal language for designers to discuss how NPCs are used in shooter games. This paper presents design patterns for NPCs in shooter games and explores their effects on gameplay. These patterns help designers communicate about and explore new ideas for enemy ...

This article intends to sketch a theory of the player drawing from psychological personality theories (Assagioli's Psychosynthesis), neurophysiologic studies (Damasio and Pert) and previous work on player's theory with the purpose of tracing a functional procedure for designing game worlds. I will make use of the concept of sub-personalities to show how potentially, all player-types coexist within the implied player. Once player types are individuated I intend to show how a "flow" path for each one of them can be planned and included during the design phase of game worlds.

Gameplay in single-player shooter games primarily consists of combat with Non-player Characters (NPCs). However, there has been little research done to study how enemy NPCs affect player behavior in shooter games. As a consequence, there is no formal language for designers to discuss how NPCs are used in shooter games. This paper presents design patterns for NPCs in shooter games and explores their effects on gameplay. These patterns help designers communicate about and explore new ideas for enemy ...

As player demographics broaden it has become important to understand variation in player types. Improved player models can help game designers create games that accommodate a range of playing styles, and may also facilitate the design of systems that detect the currently-expressed player type and adapt dynamically in real-time. Existing approaches can model players, but most focus on tracking and classifying behaviour based on simple functional metrics such as deaths, specific choices, player avatar attributes, and completion times. We describe a novel approach which seeks to leverage expert domain knowledge using a theoretical framework linking behaviour and game design patterns. The aim is to derive features of play from sequences of actions which are intrinsically informative about behaviour—which, because they are directly interpretable with respect to psychological theory of behaviour, we name ‘Behavlets’. We present the theoretical underpinning of this approach from research areas including psychology, temperament theory, player modelling, and game composition. The Behavlet creation process is described in detail; illustrated using a clone of the well-known game Pac-Man, with data gathered from 100 participants. A workshop-based evaluation study is also presented, where nine game design expert participants were briefed on the Behavlet concepts and requisite models, and then attempted to apply the method to games of the well-known first/third-person shooter genres, exemplified by ‘Gears of War’, (Microsoft). The participants found 139 Behavlet concepts mapping from behavioural preferences of the temperament types, to design patterns of the shooter genre games. We conclude that the Behavlet approach has significant promise, is complementary to existing methods and can improve theoretical validity of player models.

Feedback on player experience and behaviour can be invaluable to game designers, but there is need for specialised knowledge discovery tools to deal with high volume playtest data. We describe a study with a commercial third-person shooter, in which integrated player activity and experience data was captured and mined for design-relevant knowledge. We demonstrate that association rule learning and rule templates can be used to extract meaningful rules relating player activity and experience during combat. We ...

ABSTRACT Player experience is at the heart of good game design, but designers typically have limited experience data to work with. Detailed and fine-grained accounts of gaming experience would be of great value to designers and researchers alike, but recording such data is a significant challenge. We describe an approach based on post-game player commentaries, retrospective verbal reports cued by video of the gaming session and a word list.