基于标签的在线学习资源推荐算法

Online learning resource recommendation algorithm based on tag

在线学习是目前获取知识的一种重要途径,然而信息过载导致从在线学习平台的大量资源中找到所需的学习资源非常困难。本文提出了一种基于标签的推荐算法,混合基于内容推荐和协同过滤推荐,采用TF-IDF来平衡热门标签的权重,采用修正的余弦函数相似性计算用户间、资源间的相似性,结合学科知识图谱,让推荐结果在相似基础上增加扩展性,满足进阶学习特点。实验结果表明,本文提出的算法在准确率和推荐效率上优于传统的协同过滤推荐算法,为解决同类问题提供了较强的参考价值。

Online learning is an important way to acquire knowledge.However,the overload of information makes it very difficult to find satisfactory learning resources from a large number of resources of online learning platform.This paper proposes a tag based recommendation algorithm,which combines content-based recommendation and collaborative filtering recommendation.TF-IDF is used to balance the weight of hot tags.The modified cosine function similarity is used to calculate the similarity between users and resources.Combined with the subject knowledge map,the recommendation results can be expanded on the basis of similarity to meet the characteristics of advanced learning.Experimental results show that the proposed algorithm is superior to the traditional collaborative filtering recommendation algorithm in accuracy and recommendation efficiency,which provides a strong reference for solving similar problems.