A Semantic Recommender System for Adaptive Learning

The ever-more complex labor world and the current economic crisis ask learners and workers to continuously update their qualification levels to stay relevant on the job. Hence, education and training providers need to adjust their offerings to cope with such evolving requirements. However, the huge number of variables to consider means that finding the right learning content that lets an individual fill his or her competency gap might be difficult. The authors' semantic-based recommender system crosses heterogeneous information about learners' and workers' backgrounds as well as advertised job positions with a catalog of online courses to identify the most appropriate learning resources. Experimental observations showed a good agreement between human and automatic recommendations, confirming the applicability of the emerging semantic technology to the generation of user-centered services that can adapt to individuals' learning needs. The authors discuss the details of their system in a video Web extra at http://youtu.be/A8c5MwnlGvA. A second Web extra shows the training booklet for evaluating the authors' system and the results of the automatic recommendation; it's available at https://s3.amazonaws.com/ieeecs.cdn.csdl.public/mags/it/2015/05/mit2015050050s.pdf.