An interaction based collaborative filtering approach for personal learning environment
In this modern era of technology and information, e-learning has become an integral part of learning using these modern technologies. There are different variations or classification of e-learning but the most notable is Personal Learning Environment (PLE). Since, in a PLE system, the contents are p...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Published: |
2014
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | In this modern era of technology and information, e-learning has become an integral part of learning using these modern technologies. There are different variations or classification of e-learning but the most notable is Personal Learning Environment (PLE). Since, in a PLE system, the contents are presented to the user in a personalized manner, the problem arises regarding personalization. These days, lot information is available over internet but not every information is relevant to every user. So, in order to filter the information, different types of recommender techniques evolves. The most popular among these techniques is collaborative filtering. As the technology advances, so does the problem, similarly the recommendation techniques suffer with a very popular problem called cold-start problem. In this problem, when a new user enters in the system, due to the lack of information about the new user, the system fails to recommend contents accurately. Previously, collaborative filtering uses different approaches for recommendation like preferences profile, user ratings and tagging recommendations. In this research work a new approach is proposed to improve the recommendation accuracy for new-user cold-start problem by integrating preferences profile and tagging recommendation and utilizing the interaction among users and system. This research work takes leverage of the interaction of a new user with the PLE system and generates recommendation for this user both implicitly and explicitly thus solving new-user cold-start problem. Result shows the improvement of 31.57% in Precision, 18.29% in Recall and 8.8% in F1- measure |
|---|