Serious games have established themselves as a successful method for learning, training, an‎d changing behaviours; they combine entertainment with learning objectives. One important aspect of their successful use in learning contexts is the ability to create an‎d maintain a level of motivation an‎d engagement for the player that can be enhanced by Dynamic Difficulty Adjustment (DDA). DDA is defined as a system that is able to change a game’s difficulty automatically an‎d in real-time based on the player’s performance, preferences, an‎d emotional state. This seminar will consider the approaches to DDA that are being used in serious games today, placing them into four categories: player modelling, machine learning, affective computing, an‎d hybrid methods. A comprehensive revision of the literature indicates that despite improvements in engagement, learning outcomes, an‎d user satisfaction brought by DDA, there remains a challenge in designing models that provide appropriate levels of both technology adaptation an‎d transparency an‎d ethics. Additionally, the integration of multi-modal data an‎d more sophisticated analytics provides possibilities for developing highly adaptive an‎d immersive learning experiences. The seminar will also address implications for game designers an‎d educators an‎d focuses on framework elements that include providing real-time tracking an‎d monitoring, providing meaningful feedback, an‎d personalization in a manner that does not undermine the educational goals of serious games. This research combines, critiques, an‎d identifies gaps in the literature for the production of next generation serious games that leverage DDA to increase learning efficiency, engagement, an‎d long-term motivation.

10/28/2025 12:00:00 AM

88169

1404/08/14

A review of Dynamic Difficulty Adjustment Approaches for Video Games

Serious games , Dynamic Difficulty Adjustment , player modelling , machine learning , affective computing , hybrid approaches , engagement , learning outcomes , personalization, adaptive learning