No abstract

We noticed that learner users usually perform a set of choices or make decisions during learning, depending on the e-learning platform. This set of choices belongs to the Learner-driven Learning paradigm from Education. In this paper, we state these choices for e-learning systems, based on user-interaction partners and navigation patterns we noticed while performing a systematic review on e-learning systems. Moreover, we present how these choices are implemented in the AdaptWeb platform, a ubiquitous e-learning system for formal education.Resumo. Nós percebemos que os usuários de perfil estudante geralmente realizam um conjunto de escolhas ou tomadas de decisão durante a aprendizagem, dependendo da plataforma de e-learning utilizada. Esse conjunto de escolhas pertence ao paradigma de Aprendizagem Autodirigida da Educação. Neste artigo, definimos essas escolhas em sistemas de e-learning, com base em padrões de interação e de navegação de usuários que observamos em diferentes sistemas e-learning durante uma revisão sistemática que realizamos. Além disso, apresentamos como essas escolhas são implementadas no AdaptWeb, um sistema de e-learning formal e ubíquo.

No abstract

In this paper, we briefly review the recommendation approach of learning objects (LOs) that uses the result of the choices made by the learner user during learning (“what to learn”, “how to learn”, etc.) as a source of information. This LO recommendation approach is an implementation of collaborative filtering based on an instance-based machine learning method. The goals of this paper are: to present how to apply this LO recommendation approach in an e-learning platform used for non-formal learning – the MERLOT platform, and to perform an experimental evaluation on the MERLOT’s dataset. The evaluation showed that the LO recommendation approach presents higher prediction accuracy than the baseline approaches.

No abstract