Presuming Learner Personas from Portfolios with Non-negative Matrix Factorization
スポンサーリンク
概要
- 論文の詳細を見る
In programming course, if a teacher gives supervisions inappropriate to motivation and learning strategy of the student who asked questions to the teacher, the student may get de-motivated. In order for the teacher to give supervisions appropriate to motivation and learning strategy of a student to motivate her to study programming, the paper proposes a method to figure out the weight a student belonging to a persona. Persona is a virtual user with motivation and learning strategy representing a group of students having similar motivation and learning strategy to learn programming. Persona gives the teacher a clear image of motivation and learning strategy in contexts of student groups before the course starts. A feature matrix P representing motivation and learning strategy characteristics of the personas are figured out, by decomposing the matrix of portfolio of last course students using nonnegativematrix aproximation method. Using P of the last course, we calculate the weight from the portfolio oftiie current course. The method is being under evaluation.
- 一般社団法人電子情報通信学会の論文
- 2013-03-22
著者
-
Harada Fumiko
College Of Information Science And Engineering Ritsumeikan University
-
Phuong Dinh
Graduate School of Science and Engineering, Ritsumeikan Uni.
-
Shimakawa Hiromitsu
College of Information Science and Engineering, Ritsumeikan Uni
関連論文
- Adaptive Fair Resource Allocation for Energy and QoS Trade-Off Management
- Adaptive Fair Sharing Control in Real-Time Systems Using Nonlinear Elastic Task Models(Nonlinear Problems)
- Directing All Learners to Course Goal with Enforcement of Discipline Utilizing Persona Motivation
- Derivation of Learning Style Effectiveness from Portfolio in Programming Education
- Presuming Learner Personas from Portfolios with Non-negative Matrix Factorization
- Non-negative Matrix Factorization to Identify Motivation and Learning Strategies from Portfolio