EVALUATION OF ONLINE MOOC COURSES AND SUPPORT FOR LEARNERS’ COURSE SELECTION

Abstract

            After the pandemic circumstance, the education has tremendously changed the way in education through online. Millions of new clients have signing up on Massive Open Online Course (MOOC) providers, such as Coursera or edX, online platforms because it is standardized and decentralized system in online education. Hence, the important and curiously investigate areas in online instruction in this last decade is Personalized Group based recommendation system since the learning fashion is particular with each student. The objectives of this study investigate and legitimize the significance of students' execution in online course materials in a real-world education system by assessing data utilizing data mining techniques. Several techniques and algorithms in Data mining are used to identify the preferences of accessible a huge number of learning modes of a client in a system. Based on individual and other learners' behaviours, searches and past history, we are able effectively identify the proposals by Recommender system. This strategy can predict preferred modes of learning for a learner and after that recommends the most excellent modes of learning to a learner. The result of the investigation display how extricated learning helps in improving decision making processes. The scope of this study is to recognize the components that affect the students to select the materials of online courses in pre-graduate education. An early desire of student performance makes a move for better achievements of the student. To achieve standard quality education, a few attempts have been made to expect the performance of the student. Especially Prediction Techniques, Using data mining tools, such as Recommender System and Content-Based Filtering Algorithms help in upgrading the quality of the online course materials by assessing student data to predict the student performance within the courses.