Adaptation and Assessment (TwoA)
This asset enables a real-time automatic adaptation of game difficulty to player’s expertise level. The adaptation algorithm is a scientifically well-validated and practically proven method that is being successfully used by its original developers (Oefenweb, https://www.oefenweb.nl/) in web-based serious games (e.g., https://www.mathsgarden.com/). The asset provides a portable and highly interoperable implementation of the publicly available version of the algorithm.
The adaptation algorithm makes use of a stealth assessment algorithm that assigns difficulty ratings and expertise ratings to players and game modules respectively. The asset tracks changes in these ratings allowing assessment of players’ learning progress either by players themselves or by instructors. Therefore, the asses can be used for stealth assessment as well as for adaptation.
The asset is lightweight with minimal requirements for integrating with a game and minimal impact on the game performance. The asset is also agnostic to the game content requiring only basic performance metrics with no explicit domain knowledge.
An early version of the asset is available at Github (refer to links below). Software consists of two components: (1) a core adaptation component to be integrated with a game and (2) an exemplar standalone data visualization/analysis component. Manuals on using both components are available within the packages.