Branched learning paths for the recommendation of personalized sequences of course items

Current research in Learning Analytics is also concerned with creating personalized learning paths for students. Therefore, Recommender Systems are used to suggest the next object to learn or pre-computed paths are recommended. However, the time of the requested learning session and the freedom of choice are often not considered. Respecting certain course deadlines and providing the user with choice is a very important aspect of recommendations. In this work, we present an approach to creating personalized paths through knowledge networks. These paths are constructed by considering the time at which they are requested and suggest alternative routes to provide the user with a choice of preferred learning items. An evaluation gives precision measures that have been obtained with different lengths for the Top-N recommendations and different branching factors in the paths and compares the results with other Recommender Systems used in Adaptive Learning Environments.