An Intelligent e-Learning Course Recommendation Framework Based on Student Learning Style
Erum Ashraf, National Advanced IPv6, Universiti Sains Malaysia, Pulau Penang, Malaysia Selvakumar Manickam, National Advanced IPv6, Universiti Sains Malaysia, Pulau Penang, MalaysiaShankar Karuppayah, National Advanced IPv6, Universiti Sains Malaysia, Pulau Penang, Malaysia Sufiana Khatoon Malik, National University of Modern Languages, Islamabad, Pakistan
As the drive to move from traditional face-to-face classroom learning to e-learning is ever in demand, the knowledge corpus exposed to students can be overwhelming because there is a need to automate certain functions of the e-learning framework. One of these functions is the course recommendation feature. Course recommendations help students save time and effort to explore the courses from a large pool of resources while considering multiple attributes such as social influence, prior knowledge, and learning style. These numerous criteria make the course recommendation a complex process that requires the researcher to promote online education and intelligently assist learners in identifying the relevant online courses. Although various researchers have put forward strategies to address course recommendation problems, learning style, a critical element in ensuring effective learning, has not been considered part of the course recommendation framework. This paper puts forward a learning style-based course recommendation framework that is expected to provide highly automated decision support for learners in identifying the most suitable course to improve their efficiency in e-learning. Additionally, based on this framework, instructors can analyze and re-evaluate the courses according to students’ learning styles. The proposed framework reduces the time and effort involved in seeking relevant courses, thereby improving the learning experience.