Optimizing adaptivity in educational games

One of the most promising ways that games for learning can improve education is by adapting to each child individually. However, it is often difficult to instrument game mechanics so that they can be controlled to promote learning. Furthermore, even if this parameterization is possible, there is little knowledge of how to generate adaptive level progressions that optimize engagement and learning. We have taken the first step towards enabling adaptivity in an educational game for teaching fractions through the automatic generation of levels in a way that allows for multiple axes of mathematical and spatial difficulty to be controlled independently. We propose to expand on this work by developing a framework for representing conceptual knowledge. This framework will keep track of each player's knowledge, generate game levels that are tailored to the player's knowledge and skill level, and create progressions of these levels that allow players to learn new concepts through experimentation. We will compare multiple adaptive concept sequencing algorithms by evaluating their effects on player learning and engagement through multivariate tests with tens of thousands of players.