OERecommender : um sistema de recomendação de REA para MOOC

• Ano de defesa: 2015
• Autor(a) principal: Zuquello, Ariel Gustavo
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Estadual de Maringá; Brasil; Departamento de Informática; Programa de Pós-Graduação em Ciência da Computação; UEM; Maringá, PR; Centro de Tecnologia
• Palavras-chave em Português: Massive Open Online Course (MOOC); Recomendação de Recursos Educacionais Abertos (REAs); OERecommender (Sistema de Recomendação); Internet; Ensino à distância; Brasil.; MOOC, OER, OERecommender, Recommendation System; Brazil.; Ciências Exatas e da Terra; Ciência da Computação
• Link de acesso: http://repositorio.uem.br:8080/jspui/handle/1/2538

Massive Open Online Course (MOOC) is one of the newest trend in education at a distance. Its goal is to bring knowledge to a large body of people anywhere through the Web, in most cases free of charge. A key point of MOOCs is to provide mechanisms to support the learning process to its participants. Its population of participants is culturally diverse and the dropout rate is considered high, around 90%. One of its recognized shortcomings is the lack of support from open materials that can enrich participants' learning process. This work proposes the OERecommender, a Recommendation System of Open Educational Resources (OER) that aims to contribute to the improvement of this scenario. The OERecommender aims to support participants in searching and recovering OER that can help in their learning process. The design of the OERecommender conceptual model was based on existing and similar architectures. The similarity between users and OER was based on graph methods. Algorithms for sorting and comparison were used, respectively, to sort OER by relevance and compare instances to find the most similar context among users. Finally, a recommendation algorithm was adapted to predict which REA were most relevant to the user presenting them through a widget. In order to assess the OERecommender, simulations were performed through prototyping scenarios. The simulations indicate that the introduction of OER recommendation mechanisms in MOOC is feasible and can contribute to improve the support to its participants.