A Recommendation Education Tool

Abstract

Recommendation systems have gained a lot of interest from many authors recently, and e-learning is one of the most interesting and important fields of recommendation systems. Although e- learning is the future, at present the bulk of the information on the internet hinders the user’s discovery of appropriate content over the large databases. Existing systems for selecting relevant content to carry out research are time consuming and produce many inaccurate and irrelevant recommendations. Choosing a suitable course helps students and researchers to carry out their activity in an appropriate way. A number of recommendation systems have been proposed in the literature, however, the accuracy of these recommendations is still undetermined. These systems can be divided into different categories based upon their function and methodology. This work intended to develop a recommendation system that identifies the learning resources and material from the web along with suggesting the content of the courses. It used Google API to get the relevant search from the most popular search engines. Furthermore, it used standard filtering and Stanford Open NLP library for parts of speech (POS) tagging. Relevant contents are added to the databases and are matched using ontology. Such scheme improved the chances of the learner to get important information by providing the most appropriate recommendations. It also improved the performance that can result in increased satisfaction level of users. It performed well and mitigated some of the existing approaches’ weaknesses.