Estimating student persona through factorization of learning portfolio
Dinh Dong Phuong, Fumiko Harada, Hiromitsu Shimakawa · 2013
Estimation of motivation and learning strategy of students is crucial for a teacher to engage them in programming. Let us consider a persona, which is a virtual student representing a student group similar in motivation and learning strategy to learn programming. Personas enable the teacher to predict student behavior during the programming education course. The paper proposes a method to figure out the weight each student belongs to a specific persona. It assumes students in a persona take similar learning behavior, even in different years. To determine how strongly each student learning in the current programming course belongs to a specific persona, it examines the similarity of her learning portfolio to that of past students. It decomposes a matrix of each student portfolio into the product of 2 matrices; a matrix representing the weight of each student belonging to every persona and a matrix of persona learning behavior, using the nonnegative-matrix factorization. This paper illustrates the method to figure out the matrices effectively.