Recommendation system based on video processing in an e-learning platform

ABSTRACT

With online learning technology fatly growing, especially with the Covid-19 pandemic, learning resources are produced in massive amounts, with high heterogeneity, and in numerous media formats. The key issue for today's learners is how to access the required learning resource based on their preferences and skills? Learning videos have become the central role in e-learning of higher education institutions. As a learning content, videos prove it is an important and necessary content delivery tool in all online platforms such as online, flipped, and blended classes. Hence, indicating suitable videos in seminal years possibly will help to do research in a better way. In this article, we present a recommender system that will suggest and guide learners in choosing appropriate learning videos per their requirements. Our system is based on collective intelligence. Indeed, we analyze the comments of Internet users on the videos to extract their opinions and then compare them with the evaluations to obtain a better recommendation.