DEVELOPMENT OF A BIG DATA PLATFORM DEDICATED TO THE IMPLEMENTATION OF AN INTELLIGENT EDUCATION SYSTEM - STUDY AND IMPLEMENTATION OF THE TECHNICAL ARCHITECTURE

Most higher education institutions use limited analytical tools to examine the performance indicators of a student or a classroom from one semester to the other. Students' activities (lessons, simulations, questionnaires, discussion forums, blogs, etc.) generate thousands of transactions per student that are not collected or analyzed to identify proactively the students who can face the risk of failure or abundance. The Big Data can provide to the institutions the predictive tools to anticipate these risks, improve the learning of students and ensure quality programs. The objective of our contribution is to put in place a technical architecture for a Big Data platform Dedicated to the establishment of an intelligent teaching. This platform aims (1) A recording of massive manuals developed by teachers, (2) monitoring and storing the activities carried out by the students through these manuals as well as (3) The use of Big Data tools to Collect, analyze the data related to these activities and (4) Provide report and statistics to the teacher and for administrators to be able to (5) adapt the content of the manuals (6) and follow individual students in their progression of learning. The modeling solution adopted consists in a hybridization of (1) LOM (Learning Object Meta Data) to describe the educational objects forming the manuals and build a catalog of resources to keep the interoperability with other systems for the management of learning and (2) xAPI (Experience Application Program Interface or Tin Can API) to trace the activities of students who will be saved in a warehouse LRS (Learning Record Store). The Big Data tools are used to collect and analyze the data of the manuals content as well as the activities of the students. To ensure the interoperability with other systems, our platform is based on a REST API. We have implemented the solution NoSQL database oriented document as advocated the standard LRS, for the storage of documents. To test our solution, we have developed an application for tracking in real-time the testing activities. This application leverages Streaming processing power guaranteed by our Big Data platform. Our application also allows each teacher to have a dynamic dashboard which displays the results of each student. Our application allows the teacher to: (1) see in real time the students having blockages and intervene to help them to overcome these blockages. (2) Identify the gaps for each student. (3), and accordingly, strengthen or adapt the content delivered to anticipate any risk of failure among students. The exploration of the results stored on the activities of the students should enable 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.