Dynamic Game Difficulty Balancing in Real Time Using Evolutionary Fuzzy Cognitive Maps

Perez, Lizeth Joseline Fuentes; Calla, Luciano Arnaldo Romero; Valente, Luis; Montenegro, Anselmo; Clua, Esteban

doi:10.1109/sbgames.2015.17

Cited by 10 publications

(4 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In most studies, the input performance/physiological measures are classified into two, three or more levels of a psychological dimension. Previous studies have used either supervised ML methods such as linear discriminant analysis (LDA) (Chanel et al, 2011), support vector machines (SVM) (Ma et al, 2015), logistic regression (Perez et al, 2015), and artificial neural networks (Casson, 2014) or unsupervised ML methods such as Gaussian mixture models (Lee and Jung, 2006) and k -means clustering (Kim et al, 2009). The last few years have also seen an emerging trend of using deep learning in affective computing (Glorot et al, 2011; Jirayucharoensak et al, 2014) due to its flexibility and good performance in non-linear classification.…”

Section: Introductionmentioning

confidence: 99%

Classification of Multiple Psychological Dimensions in Computer Game Players Using Physiology, Performance, and Personality Characteristics

et al. 2019

View full text Add to dashboard Cite

Human psychological (cognitive and affective) dimensions can be assessed using several methods, such as physiological or performance measurements. To date, however, few studies have compared different data modalities with regard to their ability to enable accurate classification of different psychological dimensions. This study thus compares classification accuracies for four psychological dimensions and two subjective preferences about computer game difficulty using three data modalities: physiology, performance, and personality characteristics. Thirty participants played a computer game at nine difficulty configurations that were implemented via two difficulty parameters. In each configuration, seven physiological measurements and two performance variables were recorded. A short questionnaire was filled out to assess the perceived difficulty, enjoyment, valence, arousal, and the way the participant would like to modify the two difficulty parameters. Furthermore, participants’ personality characteristics were assessed using four questionnaires. All combinations of the three data modalities (physiology, performance, and personality) were used to classify six dimensions of the short questionnaire into either two, three or many classes using four classifier types: linear discriminant analysis, support vector machine (SVM), ensemble decision tree, and multiple linear regression. The classification accuracy varied widely between the different psychological dimensions; the highest accuracies for two-class and three-class classification were 97.6 and 84.1%, respectively. Normalized physiological measurements were the most informative data modality, though current game difficulty, personality and performance also contributed to classification accuracy; the best selected features are presented and discussed in the text. The SVM and multiple linear regression were the most accurate classifiers, with regression being more effective for normalized physiological data. In the future, we will further examine the effect of different classification approaches on user experience by detecting the user’s psychological state and adapting game difficulty in real-time. This will allow us to obtain a complete picture of the performance of affect-aware systems in both an offline (classification accuracy) and real-time (effect on user experience) fashion.

show abstract

Section: Introductionmentioning

confidence: 99%

Classification of Multiple Psychological Dimensions in Computer Game Players Using Physiology, Performance, and Personality Characteristics

et al. 2019

View full text Add to dashboard Cite

show abstract

“…As a result, gamers may unknowingly withdraw their effort and then discontinue the game altogether upon seeing an unsatisfactory ratio of achieved results to subjectively assessed (overestimated) commitment. In the context of MIT and our results, systems such as the decades-old gradual increase in the difficulty of the game without player intervention (e.g., Tetris) or the relatively new dynamic game difficulty balancing [33] offer a much wider possibility of adjusting the difficulty of a game to potential motivation, thereby engaging the gamer. On the other hand, both these solutions are more demanding for a game developer, therefore further research in the MIT paradigm may help make it easier to create games that take into account the individual needs of the player.…”

Section: Plos Onementioning

confidence: 78%

“…In the case of dynamic game difficulty balancing, there are two basic challenges: which variables should be included in the difficulty-balancing models, and how can these variables be measured? The solutions used so far in the field of models often boil down to the use of fuzzy models, which is sometimes effective [33]. However, taking a step back and looking at the phenomenon from the broader theoretical perspective offered by MIT may in some cases help to see the importance of previously ignored variables, such as fatigue [35], affect [36], success importance [37] and others, whose influence on this complex relationship has been repeatedly proven empirically [38,39].…”

Section: Plos Onementioning

confidence: 99%

Player involvement as a result of difficulty: An introductory study to test the suitability of the motivational intensity approach to video game research

Strojny

Strojny²,

Rębilas³

2023

PLoS ONE

View full text Add to dashboard Cite

Motivational Intensity Theory could serve as a useful framework in the process of analyzing and optimizing a user’s involvement in computer games. However, it has not yet been used in this way. Its main advantage is that it makes clear predictions regarding the relations between difficulty level, motivation and commitment. The current study aimed to test whether the postulates of this theory may be useful in the process of game development. Forty-two participants took part in a fully controlled within-subjects experiment utilizing a commonly available game (Icy Tower) that has several levels of difficulty. Participants played on four increasing levels of difficulty and their task was to play as best they could, with the aim of reaching the hundredth platform. As a result, we demonstrated that involvement level increases as the difficulty level increases when a task is feasible, but it drops rapidly when a task is so difficult that it cannot be completed. This is the very first evidence that Motivational Intensity Theory may be useful in game research and design. The following study also supports concerns regarding the usefulness of self-report data in the game design process.

show abstract

“…However, players may have different skills; what is classified as difficult, a player may perceive to be very easy or very difficult, which can lead players to feeling frustrated or even bored, which decreases their motivation and engagement with a game [ 40 ].…”

Section: Discussionmentioning

confidence: 99%

A Serious Game (Immunitates) About Immunization: Development and Validation Study

Lima¹,

Leon²,

Ribeiro³

et al. 2022

JMIR Serious Games

View full text Add to dashboard Cite

Background Vaccination is a fundamental part of all levels—local to worldwide—of public health, and it can be considered one of humanity's greatest achievements in the control and elimination of infectious diseases. Teaching immunization and vaccination can be monotonous and tiring. It is necessary to develop new approaches for teaching these themes in nursing school. Objective We aimed to develop and validate a serious game about immunization and vaccination for Brazilian nursing students. Methods We developed a quiz-type game, Immunitates, using design and educational theoretical models and Brazilian National Health Guidelines. The game’s heuristics and content were evaluated with 2 different instruments by a team of experts. A sample of nursing students evaluated the validity of the game’s heuristics only. We calculated the content validity index (CVI) for each evaluation. Results The study included 49 experts and 15 nursing students. All evaluations demonstrated high internal consistency (Cronbach α≥.86). The game’s heuristics (experts: CVI 0.75-1.0; students: CVI 0.67-1.0) and the game’s contents demonstrated validity (experts: CVI 0.73-1.0). Participants identified some specific areas for improvement in the next version. Conclusions The serious game appears to be valid. It is intended as a support tool for nursing students in the teaching–learning process and as a tool for continuing education for nurses.

show abstract

Dynamic Game Difficulty Balancing in Real Time Using Evolutionary Fuzzy Cognitive Maps

Cited by 10 publications

References 9 publications

Classification of Multiple Psychological Dimensions in Computer Game Players Using Physiology, Performance, and Personality Characteristics

Classification of Multiple Psychological Dimensions in Computer Game Players Using Physiology, Performance, and Personality Characteristics

Player involvement as a result of difficulty: An introductory study to test the suitability of the motivational intensity approach to video game research

A Serious Game (Immunitates) About Immunization: Development and Validation Study

Contact Info

Product

Resources

About