A folksonomy-based recommender system for learning material prediction

The Internet is a network where information, data and services can be accessed rapidly. Also in the area of eLearning it is common to access your learning material online to speed up the distribution and keep the retrieve of documents easy. Thus, the variety of learning material increases, since teachers provide scripts and slides, but also further online materials and services like lecture recordings or audio podcasts. To choose from a wideranging pool of material seems to be an advantage at first, but can also lead to disorganization, mental overload, ignorance of unknown material and misunderstanding of content. Many Internet services provide assistive systems so called Recommender Systems (RS), which help users to find the most important or interesting information and to overcome the mental overload. Those services may also be useful in the area of eLearning to counteract those reasons given above. In this paper we present the development of such a RS on the basis of a folksonomy approach to predict learning material in higher education classes and to optimize students learning processes.