Intelligent Database Systems Lab 國立雲林科技大學 National Yunlin University of Science and Technology 1 Automatic Recommendations for E-Learning Personalization Based on Web Usage Mining Techniques and Information Retrieval Presenter : Cheng-Han Tsai Authors : Mohamed Koutheair Khribi, Mohamed Jemni, Olfa Nasraoui ETS, 2009
Intelligent Database Systems Lab N.Y.U.S.T. I. M. 2 Outlines Motivation Objectives Methodology Experiments Conclusions Comments
Intelligent Database Systems Lab N.Y.U.S.T. I. M. 3 Motivation Most e-learning platforms are still delivering the same educational resources to learners Most e-learning platforms have not been personalized
Intelligent Database Systems Lab N.Y.U.S.T. I. M. Objectives 4 To build an automatic recommendations in e- learning platforms
Intelligent Database Systems Lab N.Y.U.S.T. I. M. 5 Methodology offline online Content models Learner model CF + KNN & CBF + TF-IDF CF & Cosine Similarity & Apriori algorithm & Association Rules & Confidence CBF & LOM & Inverted Index
Intelligent Database Systems Lab N.Y.U.S.T. I. M. Methodology 6 Learner model Confidence
Intelligent Database Systems Lab N.Y.U.S.T. I. M. Methodology Using the open source search engine Nutch in content model- ing followed by CBF Automatically generates invert- ed index 7 Content model
Intelligent Database Systems Lab N.Y.U.S.T. I. M. Methodology 8
Intelligent Database Systems Lab N.Y.U.S.T. I. M. Experiments 9
Intelligent Database Systems Lab N.Y.U.S.T. I. M. Experiments 10
Intelligent Database Systems Lab N.Y.U.S.T. I. M. Conclusions The proposed approaches can provide adaptive learning objects to different users The recommendation system can compute against massive repository of educational resources in "real time". 11
Intelligent Database Systems Lab N.Y.U.S.T. I. M. 12 Comments Advantages ─ Integration of many approaches in this paper Applications ─ IR