An open source hybrid learning object recommender system based on Europeana

Resumen

Learning object repositories play a crucial role in the distribution of educational content by providing users with access to wide collections of learning objects. Nevertheless, users often have difficulties in locating learning objects of interest from very large repositories. A measure that these repositories can adopt to address this problem is the use of recommender systems to provide users with learning object recommendations. This paper presents an open source hybrid learning object recommender system called EuropeanaRS which is capable of generating recommendations of learning objects retrieved from Europeana, one of the most popular repositories in the cultural heritage domain. The paper also describes how EuropeanaRS was used in a tool called Newspaper Exploration Environment to provide a recommendation feature. EuropeanaRS was evaluated in terms of accuracy, utility, user satisfaction and usability. An evaluation of the Newspaper Exploration Environment was also carried out. The results of the evaluations show that EuropeanaRS had a good accuracy, achieved high perceived usefulness, obtained high user satisfaction, was easy to use, was able to generate recommendations that significantly outperformed random recommendations, and that it can be used with success for enriching tools by providing learning object recommendations.