A novel adaptive e-learning model based on Big Data by using competence-based knowledge and social learner activities

The e-learning paradigm is becoming one of the most important educational methods, which is a decisive factor for learning and for making learning relevant. However, most existing e-learning platforms offer traditional e-learning system in order that learners access the same evaluation and learning content. In response, Big Data technology in the proposed adaptive e-learning model allowed to consider new approaches and new learning strategies. In this paper, we propose an adaptive e-learning model for providing the most suitable learning content for each learner. This model based on two levels of adaptive e-learning. The first level involves two steps: (1) determining the relevant future educational objectives through the adequate learner e-assessment method using MapReduce-based Genetic Algorithm, (2) generating adaptive learning path for each learner using the MapReduce-based Ant Colony Optimization algorithm. In the second level, we propose MapReduce-based Social Networks Analysis for determining the learner motivation and social productivity in order to assign a specific learning rhythm to each learner. Finally, the experimental results show that the presented algorithms implemented on Big Data environment converge much better than those implementations with traditional concurrent works. Also, this work provides main benefit because it describes how Big Data technology transforms e-learning paradigm.