Abstract:

We live in a world where huge amounts of data are collected every day - terabytes or petabytes of data pouring into our computer networks, Internet and various devices for data storage business, society, science and engineering, medicine and almost every other aspect of daily life. This explosive growth of information in education has become available as a result of the increasing of deployment of Learning Management Systems (LMS). These systems generate massive amounts of data, including different logs like learners’ activities, courses’ activities, course contents, student assessments results and many others. Analysis of these data is an important necessity in order to achieve better student results.

To address such problems, we propose an approach for semantic recommendation, semantic search, and semantic similar resources of different types of learning resources. To describe further and illustrate our proposed approach, a system architecture are also presented in this paper.

In order for the system to provide semantic recommendation, the available information for each learner would be used, as well as aggregated statistics on the behavior of a group of learners. The information will be extracted from the database and through machine learning techniques, the system will analyze and generate personal recommendations. On the other side to achieve , semantic search of resources containing materials related to the search term from the subject area, it will use ontology for the concepts and relationships between them in the subject area in which the educational platform is specialized.

Keywords:

Semantic recommendation system, LMS, data analysis, resource annotation.