کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
378869 | 659230 | 2013 | 16 صفحه PDF | دانلود رایگان |
![عکس صفحه اول مقاله: Application of implicit and explicit attribute based collaborative filtering and BIDE for learning resource recommendation Application of implicit and explicit attribute based collaborative filtering and BIDE for learning resource recommendation](/preview/png/378869.png)
Explosive growth of e-learning in the recent years has caused difficulty of locating appropriate learning resources to learners in these environments. Recommender system is a promising technology in e-learning environments to present personalized offers and deliver suitable learning resources for supporting activity of users. Compared with resource recommendation in e-commerce systems, users in e-learning systems have topic preferences in e-learning systems. However, e-learning systems have their own characteristics and current e-commerce algorithms cannot effectively use these characteristics to address needs of recommendations in these environments. To address requirement of e-learning resource recommendation, this research uses attribute of resources and learners and the sequential patterns of the learner's accessed resource in recommendation process. Learner Tree (LT) is introduced to take into account explicit multi-attribute of resources, time-variant multi-preference of learner and learners' rating matrix simultaneously. Implicit attributes are introduced and discovered using matrix factorization. BIDE algorithm also is used to discover sequential patterns of resource accessing for improving the recommendation quality. Finally, the results recommendation of implicit and explicit attribute based collaborative filtering and BIDE are combined. The experiments show that our proposed method outperforms the previous algorithms on precision and recall measures and the learner's real learning preference can be satisfied accurately according to the real-time up dated contextual information.
Journal: Data & Knowledge Engineering - Volume 87, September 2013, Pages 130–145