Quality Prediction of Open Educational Resources A Metadata-based Approach
share
Open Educational Resources (OERs) are openly licensed educational materials that are widely used for learning. Nowadays, there are many online learning systems and learning content repositories providing millions of open educational materials. Currently, it is very difficult for learners to find the most appropriate and high quality OER among all of these resources. In this respect, OER metadata are crucial for providing high-quality services such as search and recommendation. Furthermore, metadata facilitate the process of automatic OER quality control as the continuously increasing number of OERs makes manual quality control extremely difficult. In this work, we collected the metadata of 8,887 OERs in order to perform an exploratory data analysis on how to automatically assess the quality of OER with respect to its metadata. Based on our study, we could demonstrate that OER metadata and content are closely related. Accordingly, we propose an OER metadata scoring model, and a prediction model to anticipate the quality of OERs. Based on our data and model, we could detect high-quality OERs with accuracy of 94.6. We evaluated our model on 841 educational videos to show that our model can be applied on other open educational repositories.
READ FULL TEXT