Player behavioural modelling has grown from a means to improve the playing strength of computer programs that play classic games (e.g., chess), to a means for impacting the player experience and satisfaction in video games, as well as in cross-domain applications such as interactive storytelling. In this context, player behavioural modelling is concerned with two goals, namely (1) providing an interesting or effective game AI on the basis of player models and (2) creating a basis for game developers to personalise gameplay as a whole, and creating new user-driven game mechanics. In this article, we provide an overview of player behavioural modelling for video games by detailing four distinct approaches, namely (1) modelling player actions, (2) modelling player tactics, (3) modelling player strategies, and (4) player profiling. We conclude the article with an analysis on the applicability of the approaches for the domain of video games.
DOCUMENT
With the increased adoption of real-time objective measurements of player experience, advances have been made in characterising the dynamically changing aspects of the player experience during gameplay itself. A direct coupling to player action, however, is not without challenges. Many physiological responses, for instance, have an inherent delay, and often take some time to return to a baseline, providing challenges of interpretation when analysing rapidly changing gameplay on a micro level of interaction. The development of event-related, or phasic, measurements directly coupled to player actions provides additional insights, for instance through player modelling, but also through the use of behavioural characteristics of the human computer interaction itself. In this study, we focused on the latter, and measured keyboard pressure in a number of different, fast-paced action games. In this particular case, we related specific functional game actions (keyboard presses) to experiential player behaviour. We found keyboard pressure to be higher for avoidance as compared to approach-oriented actions. Additionally, the difference between avoidance and approach keyboard pressure related to levels of arousal. The findings illustrate the application potential of qualifying players’ functional actions at play (navigating in a game) and interpret player experience related to these actions through players’ real world behavioural characteristics like interface pressure.
MULTIFILE
This paper presents a method for generating player-driven narratives from visual inputs by exploring the visual analysis capabilities of multimodal large language models. By employing Bartle’s taxonomy of player types—Achievers, Explorers, Socializers, and Killers—our method creates stories that are tailored to different player characteristics. We conducted a fourfold experiment using a set of images extracted from a well-known game, generating distinct narratives for each player type that are aligned with the visual elements of the input images and specific player motivations. By adjusting narrative elements to emphasize achievement for Achievers, exploration for Explorers, social connections for Socializers, and competition for Killers, our system produced stories that adhere to established narratology principles while resonating with the characteristics of each player type. This approach can serve as a helping tool for game designers, offering new insights into how players might engage with game worlds through personalized image-driven narratives.
LINK
New online stores and digital distribution methods have led to the development of alternative monetization models for video-games, such as free-to-play games with advertisements. Although there are many games using such models, until now the effect on the player experience from such interruptions has not been studied. In this controlled experiment, we requested that participants (N=236) play one of three different versions of a platformer game with: 1) no interruptions, 2) 30-second video advertisements, and 3) a multiple-choice questionnaire. We then evaluated the effects on the player experience. The study shows differences in their experiences, namely in: competence, immersion, annoyance, affects, and the reliability of the questionnaire answers. The contribution of this work is to identify which player experience variables are affected by interruptions, which can be valuable for selecting the business model and guiding the game design process.
LINK
Trying to understand a player's characteristics with regards to a computer game is a major line of research known as player modeling. The purpose of player modeling is typically the adaptation of the game itself.We present two studies that extend player modeling into player profiling by trying to identify abstract personality traits, such as the need for cognition and self-esteem, through a player's in-game behavior.We present evidence that game mechanics that can be broadly adopted by several game genres, such as hints and a player's self-evaluation at the end of a level, correlate with the aforementioned personality traits. We conclude by presenting future directions for research regarding this topic, discuss the direct applications for the games industry, and explore how games can be developed as profiling tools with applications to other contexts.
LINK
Player Modeling is a research field that studies player characteristics by analyzing in-game behavior. We aim to develop independent models, which are transferable and useful beyond a game’s context. We shall demonstrate the feasibility of this approach by applying player models to crowdsourcing to predict workers’ task completion effectiveness. Specifically, we model a user’s Need for Cognition based on in-game behavior, and based on that try to assign appropriate tasks to workers.
LINK
Player behavior during game play can be used to construct player models that help adapt the game and make it more fun for the player involved. Similarly in-game behavior could help model personality traits that describe people's attitudes in a fashion that can be stable over time and over different domains, e.g., to support health coaching, or other behavior change approaches. This paper demonstrates the feasibility of this approach by relating Need for Cognition (NfC) a personality trait that can predict the effectiveness of different persuasion strategies upon users to a commonly used game mechanic - hints. An experiment with N=188 participants confirmed our hypothesis that NfC has a negative correlation with the number of hints players follow during the game. Future work should confirm if adherence to hints can be used as a predictor of behavior in different games, and to find other game mechanics than hints, that help predict user traits.
DOCUMENT
Player behavior during game play can be used to construct player models that help adapt the game and make it more fun for the player involved. Similarly in-game behavior could help model personality traits that describe people's attitudes in a fashion that can be stable over time and over different domains, e.g., to support health coaching, or other behavior change approaches. This paper demonstrates the feasibility of this approach by relating Need for Cognition (NfC) a personality trait that can predict the effectiveness of different persuasion strategies upon users to a commonly used game mechanic - hints. An experiment with N=188 participants confirmed our hypothesis that NfC has a negative correlation with the number of hints players follow during the game. Future work should confirm if adherence to hints can be used as a predictor of behavior in different games, and to find other game mechanics than hints, that help predict user traits.
DOCUMENT
In this paper we analyse the way students tag recorded lectures. We compare their tagging strategy and the tags that they create with tagging done by an expert. We look at the quality of the tags students add, and we introduce a method of measuring how similar the tags are, using vector space modelling and cosine similarity. We show that the quality of tagging by students is high enough to be useful. We also show that there is no generic vocabulary gap between the expert and the students. Our study shows no statistically significant correlation between the tag similarity and the indicated interest in the course, the perceived importance of the course, the number of lectures attended, the indicated difficulty of the course, the number of recorded lectures viewed, the indicated ease of finding the needed parts of a recorded lecture, or the number of tags used by the student.
LINK
To prevent the social worker being jammed between the economic and rationalized logic of managers and politicians on the one hand, and the life world of the people on the other, he needs to develop a healthy identity. The social constructive view can help to overcome the identity crisis the social professional is in. It offers a model to analyze the conflict a social professional has to deal with, and forces the social worker to make a clear and moral choice for the life world of his clients. This view seems also suitable to develop an indigenous body of practice theory for social work. The presence theory, the family group work and constructive social work demonstrates the possibilities. To regain confidence from both the people and the politicians, the rationalized system of planning and control has to be replaced by the trust model. To develop this model we have to find ways to justify the money used in this sector.
DOCUMENT
