Using Non-Negative Matrix Factorization to Cluster Learners and Construct Learning Communities

In an e-learning environment, learning community is an effective solution to conquer feelings of loneliness and to share experiences and resources with one another quickly and efficiently for learners. How to cluster learners who share the same interest is a very active area of research. This paper...

Full description

Saved in:
Bibliographic Details
Published in:电子学报：英文版 2011-04, Vol.20 (2), p.207-211
Main Author: ZHANG Tongzhen SHEN Ruimin LU Hongtao
Format: Article
Language:English
Subjects:
因式分解
学习型
学习环境
学习过程
社区
群集
评价矩阵
非负矩阵分解
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In an e-learning environment, learning community is an effective solution to conquer feelings of loneliness and to share experiences and resources with one another quickly and efficiently for learners. How to cluster learners who share the same interest is a very active area of research. This paper draws knowledge point evaluation matrix from routine learning process; factorize this knowledge point evaluation matrix by Non-negative matrix factorization （NMF）; use the result of factorization to build learning communities and the relation between learners and learning communities. As a result, learners with similar interests are automatically grouped into the same community; and each learner is associated with several communities according to his or her multiple interests. The algorithms were evaluated in an online college involving 1200 students. The evaluation showed the effectiveness and efficiency of the algorithms.
ISSN:1022-4653