Optimal Gamification of Self-Directed Learning: A Computational Method and its Real-World Evaluation in an App for Learning English

The rise of online learning has transformed education beyond the classroom setting. In online education, it is popular to motivate learners through gamified learning activities. One common approach to gamification involves awarding points based on learners' performance to encourage them to engage in learning activities. However, designing an optimal point system is still an art rather than a science, and many point systems inadvertently incentivize unintended behaviors that hurt student learning. We propose a scalable computational method for designing point systems that avoid those pitfalls and motivate students to choose the activities they will learn from the most. Our method calculates a point system that aligns the learning activities' short-term appeal with their long-term learning benefits. This intelligent incentive system monitors learners' progress and adjusts the number of points the learner can earn for alternative activities accordingly. As a proof-of-concept, we applied our method to design an optimal point system for game-based second-language learning ("approximated brain points") and tested it in both a simulated language learning task and in Dawn of Civilization, an English learning application. The results of both experiments demonstrate that Brain Points effectively enhance learning outcomes and motivate students to practice skills they have not yet mastered. The successful proof-of-concept and the findings of our experiments highlight the potential of our method to design effective nudges for technology-enhanced learning.