A Bayesian Model for Learning Using Flashcards

Report published in the Proceedings of the National Conference on "Education and Research in the Information Society", Plovdiv, May, 2015

Memorising large amounts of unstructured information and vocabulary is required when studying foreign language, law, biology and medicine. Distributed over time review sessions benefit the long-term retention more than massed practice when studying such material. Flashcard learning using spaced repetition is one implementation of the distributed technique. This paper proposes a Bayesian bandit algorithm which tries to maximise the number of presented flashcards that the user is going to guess wrong in a study session. The suggested model is implemented in a mobile application.

Association for the Development of the Information Society, Institute of Mathematics and Informatics Bulgarian Academy of Sciences, Plovdiv University "Paisii Hilendarski"