Time-decayed User Profile for Second Language Vocabulary Learning System

Vocabulary learning is the foundation of second language learning. Many E-learning systems have been developed to help learners to learn vocabulary efficiently. Most of these systems employ Ebbinghaus Forgetting Curve to make the review schedule for learners. However, learners are different in learning ability and the review schedule based on Ebbinghaus Forgetting Curve may be not fit for every learner. To solve the problem, this paper proposes the timedecayed user profile (TUP) to store the personalized Forgetting Curves for each learner. First, TUP is defined and then two algorithms, TUP Training Data Generation algorithm and TUP updating algorithm, are designed to train TUP. The experimental results show that the proposed time-decayed user profile can model the personalized learning characteristics of learners accurately.