Towards an educational recommendation system based on big data techniques-case of Hadoop

Nowadays, learning and teaching must be taken to a higher level. in order for teacher to be able to examine the performance indicators of a student or a classroom from one semester to the other, and for learners to avoid endless or non-interesting results while searching and dealing with educational documents which he /she needs, we contribute this project to put in place a technical architecture for a big data platform aiming for the establishment of an intelligent teaching that best meets the needs of learners. The solution is given by the use of Big data tools and computing algorithms to collect, analyse the data related to learners activities, provide reports and statistics to the teacher, and to follow individual students in their progression of learning, besides of making it easier for students to learn without making a big effort in researches through millions of documents that have nothing to do with their learning. The modelling solution is based on building a catalogue of resources to keep the interoperability with other systems for the management of learning and to trace the activities of students that will be saved in a warehouse LRS (Learning record store). In a first step we have developed a model profile which contribute to the context, the difficulty, the interactivity level learning, and to the resource type. In the second step we want to develop a Text Mining algorithm that takes into account the diversity of languages and uses the power of the Parallel and Distributed processing of a computer cluster in order to recommend relevant documents to students. The exploration of the results stored on the activities of the students should help us in future research to develop software agents for the automatic adaptation of the contents and the real-time monitoring of the students in their learning activities, and also empower the platform with the help of translator processes provided by NLP (Natural Language Processing) techniques in case of problems related to language diversity.