Classy AA-NECTAR: Personalized Ubiquitous E-Learning Recommender System with Ontology and Data Science Techniques

Abstract

Learners have different learning styles each tailored to their own personality. Incompatibility of learning and teaching style is inconvenient. This paper integrates learner behavior modeling, academic web crawling and content retrieval using state of the art technology. This research work aims to propose a personalized ubiquitous learning model to identify learner learning styles and deploy type of content that is corresponding to the learner’s learning style. Felder-Solomon model is one of the models being used for the learner profiling. This gives ease not only to the learners but the pedagogical instructors as well for not making different type of content. Real time monitoring makes the self-adaptive system learn through the learner’s gestures and self-adjusts autonomously. Learners’ aptitude increases, saving time and inconvenience. This will give an easy access to certifying organizations to get more capable skill oriented people.