Recommender systems provide users with content they might be interested in. Conventionally, recommender systems are evaluated mostly by using prediction accuracy metrics only. But the ultimate goal of a recommender system is to increase user satisfaction. Therefore, evaluations that measure user satisfaction should also be performed before deploying a recommender system in a real target environment. Such evaluations are laborious and complicated compared to the traditional, data-centric evaluations, though. In this study, we carried out a user-centric evaluation of state-of-the-art recommender systems as well as a graph-based approach in the ecologically valid setting of an authentic social learning platform. We also conducted a data-centric evaluation on the same data to investigate the added value of user-centric evaluations and how user satisfaction of a recommender system is related to its performance in terms of accuracy metrics. Our findings suggest that user-centric evaluation results are not necessarily in line with data-centric evaluation results. We conclude that the traditional evaluation of recommender systems in terms of prediction accuracy only does not suffice to judge performance of recommender systems on the user side. Moreover, the user-centric evaluation provides valuable insights in how candidate algorithms perform on each of the five quality metrics for recommendations: usefulness, accuracy, novelty, diversity, and serendipity.

@en

Almost all studies on course recommenders in online platforms target closed online platforms that belong to a University or other provider. Recently, a demand has developed that targets open platforms. Such platforms lack rich user profiles with content metadata. Instead they log user interactions. We report on how user interactions and activities tracked in open online learning platforms may generate recommendations. We use data from the OpenU open online learning platform in use by the Open University of the Netherlands to investigate the application of several state-of-the-art recommender algorithms, including a graph-based recommender approach. It appears that user-based and memory-based methods perform better than model-based and factorization methods. Particularly, the graph-based recommender system outperforms the classical approaches on prediction accuracy of recommendations in terms of recall.@en