Semantic advisor-assisting framework to select learning materials

Selecting appropriate educational documents among enormous existing contents turns advisors into making use of some automatic content assessment systems. There exist various content assessment methods which usually consider at least one of syntactic, semantic and structural perspectives through information retrieval or machine learning algorithms. In this paper, a framework for assessing learning materials based on analytical, combinational learning algorithms is represented that is capable of assisting advisors in their selection for recommending those contents to students. The focus of proposed framework is on determining required fitness in educational summaries by semantic rules. The proposed framework is examined on a dataset of summaries and compared to the expert's assessment on the same learning materials. The comparison results reveal that the proposed semantic advisor-assisting framework was successful in almost 70% of cases.