DocumentCode :
2963654
Title :
A learner’s role-based multi dimensional collaborative recommendation (LRMDCR) for group learning support
Author :
Wan, Xin ; Ninomiya, Toshie ; Okamoto, Toshio
Author_Institution :
Grad. Sch. of Inf. Syst., Univ. of Electro-Commun., Chofu
fYear :
2008
fDate :
1-8 June 2008
Firstpage :
3912
Lastpage :
3917
Abstract :
This article argues for the new solution of personal recommender systems that can provide learners with suitable learning objects to learn in group learning. In order to improve the ldquoeducational provisionrdquo to implement the e-learning recommender system, we propose a new recommendation approach which has been proven to be more suitable to realize personalized recommendation based on not only learning histories but also learning activities and learning processes which is defined as LRMDCR (a learnerpsilas role-based multidimensional collaborative recommendation) by us. In the approach, firstly we use the Markov chain model to divide the group learners into advanced learners and beginner learners by using the learnerspsila learning activities and learning processes. Secondly we use the multidimensional collaborative filtering to decide the recommendation learning objects to every learner of the group. We believe our approach is more effective and efficient to group learning.
Keywords :
Markov processes; computer aided instruction; groupware; information filtering; information filters; Markov chain model; e-learning recommender system; group learning support; learner role-based multi dimensional collaborative recommendation; learning activities; learning processes; multidimensional collaborative filtering; personal recommender systems; Collaboration; Collaborative work; Electronic learning; History; Information filtering; Information filters; Information systems; Multidimensional systems; Recommender systems; Wide area networks;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 2008. IJCNN 2008. (IEEE World Congress on Computational Intelligence). IEEE International Joint Conference on
Conference_Location :
Hong Kong
ISSN :
1098-7576
Print_ISBN :
978-1-4244-1820-6
Electronic_ISBN :
1098-7576
Type :
conf
DOI :
10.1109/IJCNN.2008.4634360
Filename :
4634360
Link To Document :
بازگشت