A recommendation system for personal learning environments based on learner clicks

It is an elementary for different learners demanding for suitable learning contents in e-leaning environment. Personalized learning and recommendations are used to enhance the activities of learners in web oriented learning environment and this technology can deliver suitable learning resources to learners. The proposal of various electronic learning contents such as remote education or virtual classrooms has given a powerful impetus to the E-learning techniques. This paper models the preferences of learners using several attributes and learner’s access those by using data mining technology to lessen sparsity and cold-start problems and increase the diversity of the recommendation list. In this paper, first the materials are uploaded for the learners and then a preprocessing technique is used in order to extract the fields from the material such as material type, size and subject. Then, a threshold is assigned based on the similarity between the materials and by analyzing the number of times the access is made. Finally, ranking is done and k-means clustering algorithm is used to cluster based on the similarity threshold that is assigned to the materials.