Online language education recommendation based on personalized learning and edge computing

Abstract

The rapid development of the Internet has promoted the emergence of a large number of learning resources and online education platforms. However, massive resources and learning approaches have also led to the emergence of the information overload dilemma. This paper combines recommendation system and edge computing to implement personalized learning in online language education. First, the language learning resources are disposed from cloud centralized framework to edge-cloud based framework. Second, the frequent language resources are selected by using a waterfall hybrid recommendation algorithm in which the language resources are roughly filtered by a collaborative filtering and then the roughly filtered resources are further processed by a content based recommendation algorithm to sort according to the similarity score. The experimental results demonstrate the effectiveness of the proposed personalized learning strategy.