Distance Learning has enabled educational practices based on digital platforms, generating massive amounts of data. Several initiatives use this data to identify dropout contexts, mainly providing teacher support about student behavior. Approaches such as Active Methodologies are known as having good potential to involve and motivate students. This article presents a systematic mapping aiming to identify current Educational Data Mining and Learning Analytics methods. Besides, we identify Active Methodologies' application to mitigate dropout in Distance Learning. We evaluated 668 papers published from January 2015 to March 2020. The results indicate a growing application of Educational Data Mining and Learning Analytics to identify and mitigate students' abandonment in Distance Learning. However, studies with Active Methodologies to minimize dropout and enhance student permanence are scarce. Some works suggest Active Methods as a possible complement of Learning Analytics in dropout.

Os altos índices de evasão preocupam docentes e gestores da Educação a Distância. Existem iniciativas para mitigação desta situação, como a Mineração de Dados Educacionais (MDE) e o uso de Sistemas de Recomendação (SR). Apesar de efetivas em aspectos específicos, estas técnicas carecem de mecanismos para motivação dos alunos. Diante disso, esse artigo descreve um modelo de SR que apresenta como diferencial a integração de Metodologias Ativas com MDE para mitigar os riscos de evasão e potencializar a permanência dos alunos. Foi implementado um protótipo e realizada a avaliação de funcionalidade e aceitação. De acordo com o modelo TAM, mais de 87% dos docentes concordam com a facilidade de uso e 77% concordam que o SR pode ser útil no processo de ensino e aprendizagem dos alunos.

No abstract

No abstract

Distance Education enabled educational practices based on digital platforms. Despite its wide adoption, the high dropout rates are a reason for concern for teachers and institutional managers. There are initiatives to mitigate this situation, such as Educational Data Mining (EDM), Learning Analytics (LA), and the use of Recommendation Systems (RS). Although effective in specific aspects, these techniques lack mechanisms for students' motivation and pedagogical intervention by teachers, as they do not present methodological proposals to encourage learning. Therefore, this article describes an RS model that shows a differential integration of the pedagogical approach of Active Methodologies with the support of Educational Data Mining and Learning Analytics techniques to identify students with dropout risks and enhance permanence. For this, a prototype was implemented, and a case study was carried out with professors from two universities to assess functionality and acceptance. According to the TAM Model, more than 87% of teachers agree with the ease of use, and 77% agree that RS can be helpful in students' teaching and learning process. Therefore, the model contributes to teaching practices, encourages collaborative learning, and favors monitoring this process and the activities developed by the students.