Goal-based progression synthesis in a korean learning game
Shuhan Wang, Brandon Cohen, Sixian Yi, Jung Yun Park, Nicholas Teo, Erik Andersen · 2019
Designing educational games is difficult, and ideally designers should be able to rely on tools that take some of the burden off them by generating content automatically. Previous work in automatic level generation and sequencing for educational games has primarily focused on achieving a gradual increase of difficulty. However, engagement often comes from a sense of accomplishment after completing hard tasks [27]. For this reason, many games feature "boss levels" that are more intense. In this paper, we propose that a good progression should be goal-based, meaning that it should build up towards some hard tasks (goals) as soon as possible to create a sense of satisfaction. To achieve this, we propose a graph-based algorithm for automatically synthesizing goal-based learning progressions of user-specific length. We also introduce Katchi, a Korean language learning puzzle game that is designed to be highly parameterizable, to evaluate our synthesized progression. In an evaluation of a Korean learning game with 248 participants, our synthesized progression performed similarly to an expert-designed progression in terms of both our engagement and learning metrics, demonstrating that our algorithm is capable of automatically synthesizing goal-based progressions that are comparable to the manually created progressions.