AAU Institutional Repository

E-learning material Recommender System Using Learner Interest Modeling

Show simple item record

dc.contributor.advisor Tefera, Dr. Solomon
dc.contributor.author Sisay, Tamirat
dc.date.accessioned 2018-11-10T06:28:03Z
dc.date.available 2018-11-10T06:28:03Z
dc.date.issued 2015-11-08
dc.identifier.uri http://etd.aau.edu.et/handle/123456789/14113
dc.description.abstract Today recommender systems are widely used not only in e-commerce but in e-learning as well. They are actually used in the latter environment to suggest resources and learning materials to learners and, thus, contribute in improving the quality of both teaching and learning processes. As a result, predicting the needs of a learner and recommend e-learning resources in e-learning system has gained attention. The requirement for predicting user needs in order to recommend the user of e-learning system and improve the usability of the system can be addressed by recommending pages(resources) to the learner that are related to the interest of the user at that time. The aim of this research is to assess how effective the uses of the visiting time and visiting frequencies of pages in web based e-learning system to learner interest modeling for recommending e-learning resource. The main data source used is log file of Moodle e-learning Management System from Mekele University of which data set size of 267 sessions. And the approach we used that learner sessions are clustered according to the similar amount of time that is spent on common e-learning resources among sessions. Accordingly, if there is a similarity between the new learner session page time and the existing clustered sessions, the system uses two Methods to assigns the solution (recommended e-learning page links). The performance of the approach is measured using developed prototype system by the standard measure of relevance (IR system) precision for the two methods, where the system registers 46.3%, 51.4% precision for popularity information (Method 1) and popularity information and the Poisson parameter (Method 2) respectively. Finally, conclusion and future research directions are forwarded. en_US
dc.language.iso en en_US
dc.publisher Addis Ababa University en_US
dc.subject material Recommender System Using Learner Interest Modeling en_US
dc.title E-learning material Recommender System Using Learner Interest Modeling en_US
dc.type Thesis en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search AAU-ETD


Browse

My Account