《Just in time and relevant knowledge thanks to recommender systems and Semantic Web》.pdf

Conference ICL2010 September 15-17, 2010 Hasselt, Belgium Just in time and relevant knowledge thanks to recommender systems and Semantic Web. Plessers, Ben (1); Van Hyfte, Dirk (2); Schreurs, Jeanne (1) Organization(s): 1Hasselt University, Belgium; 2i.Know, Belgium Key words: E-learning, Recommender system, Semantic Web, Linked Data Abstract Recommender systems are software systems that supply users with information in order to help them make decisions, without users have to search for it themselves. A recommender system in an e-learning context is a software agent that tries to ”intelligently” recommend actions to a learner based on the actions of previous learners. These recommendations could be on-line activities such as doing an exercise, reading posted messages on a conferencing system, or running an on-line simulation, or could be simply a web resource. This paper will make a description for a recommender system that will make use of the Semantic Web and Linked Data. The proposed recommender system will have a Text Mining Module and a Recommender Module to make relevant, just in time suggestions to the user. 1. Introduction In a period of time where knowledge management is a very important issue and the problem of information overload is growing, there is a need for systems that can help to obtain information, knowledge and data. Nowadays, for many organisations, the knowledge of their people is the most important asset. The Internet has made information abundant, however the reliability, usefulness, and timeliness of the information is difficult to verify. The information and knowledge necessary for decision-making needs to be available and accessible in an easy way for the right person, at the time the information or knowledge is needed. This is where recommender s