Personalized exercise recommendation via implicit skills

Cognitive diagnosis methods need to assess the students' skills to provide personalized exercise recommendation. To perform this assessment, an initially hand built Q-matrix are presented to students, which would affect the recommendation results in intelligence education. However, very few previous studies have examined this exercise recommendation task on utilizing the implicit skills among exercises, in which the opinions of implicit skill might carry extra specific knowledge. We propose a data-driven frame to reconstruct Q-matrix automatically from implicit skills perspective and explore the utility of Dynamic Key-Value Memory Networks to solve this task. Experimental results demonstrate that our method has a guiding significance in pedagogical theory.