Personalized Combination Recommendation of Short Video Online Learning Resources

Abstract

Short video online learning resources are widely used in online learning classes because of their strong display ability, popularity and easiness to understand and concise content. The existing learning resource recommendation methods usually ignore the local time series dependence information and possible periodic changes of students' historic online learning rules, and are not suitable for the recommendation scenarios of short video online learning resources. Therefore, this article studies the personalized combination recommendation method of short video online learning resources. Preprocessing of short video online learning resources is carried out, including content feature analysis and candidate recommendation list generation. Then, based on the initial recommendation list, a combination recommendation model of short video online learning resources based on information enhancement and overlapping information of knowledge points is proposed, and the construction ideas of the model are described in detail. Experimental results verify the effectiveness of the model.

A New Methodology for Clustering of Online Learning Resources Based on Students' Learning Styles

“…Thanks to the development of Internet technology, online learning resources have been greatly enriched and now they are a crucial part of contemporary education [1][2][3][4]. Via Internet, students can access massive learning resources, such as course videos, learning materials, exercise questions, and online tutorials [5], however, it is a difficult job for students to choose the right learning resources for themselves A New Methodology for Clustering of Online Learning Resources Based on Students' Learning Styles from such massive amounts of learning resources [6][7][8][9].…”