文章基本信息

标题：Comparative Evaluation of Four Multi-Label Classification Algorithms in Classifying Learning Objects
本地全文：下载
作者：Asma Aldrees ; Azeddine Chikh ; Jawad Berri 等
期刊名称：Computer Science & Information Technology
电子版ISSN：2231-5403
出版年度：2016
卷号：6
期号：2
页码：107-124
DOI：10.5121/csit.2016.60210
出版社：Academy & Industry Research Collaboration Center (AIRCC)
摘要：The classification of learning objects (LOs) enables users to search for, access, and reuse themas needed. It makes e-learning as effective and efficient as possible. In this article the multilabellearning approach is represented for classifying and ranking multi-labelled LOs, whereaseach LO might be associated with multiple labels as opposed to a single-label approach. Acomprehensive overview of the common fundamental multi-label classification algorithms andmetrics will be discussed. In this article, a new multi-labelled LOs dataset will be created andextracted from ARIADNE Learning Object Repository. We experimentally train four effectivemulti-label classifiers on the created LOs dataset and then, assess their performance based onthe results of 16 evaluation metrics. The result of this article will answer the question of: what isthe best multi-label classification algorithm for classifying multi-labelled LOs?
关键词：Learning object; data mining; machine learning; multi-label classification; label ranking.