Latent Skill Embedding for Personalized Lesson Sequence Recommendation
This addresses the challenge of improving education quality through personalized learning for students in online courses, representing an incremental advancement in adaptive learning technology.
The paper tackles the problem of personalizing lesson sequences for students in online courses by introducing the Latent Skill Embedding (LSE) model, which learns representations from access traces to recommend sequences that help prepare for assessments, showing competitive prediction of assessment results and discrimination between sequences leading to mastery or failure.
Students in online courses generate large amounts of data that can be used to personalize the learning process and improve quality of education. In this paper, we present the Latent Skill Embedding (LSE), a probabilistic model of students and educational content that can be used to recommend personalized sequences of lessons with the goal of helping students prepare for specific assessments. Akin to collaborative filtering for recommender systems, the algorithm does not require students or content to be described by features, but it learns a representation using access traces. We formulate this problem as a regularized maximum-likelihood embedding of students, lessons, and assessments from historical student-content interactions. An empirical evaluation on large-scale data from Knewton, an adaptive learning technology company, shows that this approach predicts assessment results competitively with benchmark models and is able to discriminate between lesson sequences that lead to mastery and failure.