Relevance Ranking of Learning Objects based on Usage and Contextual Information

Traditional mechanisms used to rank learning objects are not longer viable thanks to the current abundance of resources. This work proposes the construction of an improved relevance ranking function based on contextualized attention data extracted from the interaction between the users and the objects. A multidimensional approach to relevance is followed. Beside the Algorithmic relevance, currently used in most ranking functions for learning objects, another three more subjective types of relevance are estimated: Topical, Pertinence and Situational. These four types are linearly combined into a holistic relevance ranking. This work also proposes how this combined function could be efficiently calculated and implemented as a Ranked Search service inside existing e-learning tools.