资源标签在信息爆炸时代具有不可或缺的作用,利用标签能够在很大程度上减轻推荐系统的工作量,提高其准确度.基于国家公共文化云平台资源,本文设计一种基于资源标签相关性的公共文化资源推荐方法.首先,提出BERT-GSTCNN模型(Integrating Global Semantics BERT TextCNN Model),该模型通过挖掘资源文本的局部及整体与标签之间的深度语义关系,得到资源与标签间文本相关性;然后,基于TF-IDF算法挖掘资源与标签间关键词相关性;最后,通过感知器模型将二者相融合得到资源与标签的相关性,最终得到公共文化标签资源推荐序列.分别在Reuters-21578和国家公共文化云数据集上进行多组实验,结果表明该方法资源推荐效果优于基线模型.
Abstract
Resource labels play an indispensable role in the era of information explosion,and the use of labels can greatly re-duce the workload of recommendation systems and improve their accuracy.A public cultural resource recommendation method based on the relevance of resource labels is designed based on the resources of the national public cultural cloud platform.Firstly,the Integrating Global Semantics BERT TextCNN Model is proposed,which extracts the deep semantic relationships be-tween local and global resource texts and labels to obtain the text correlation between resources and labels.Secondly,the key-word correlation between resources and labels is mined based on the TF-IDF algorithm.Finally,the correlation between re-sources and labels is obtained by using perceptron model and the recommended sequence of public cultural label resources is ulti-mately obtained.Multigroup experiments are conducted on the Reuters-21578 and National Public Culture Cloud datasets.The experiments results show that the resource recommendation effect of our method is superior to the baseline model.
关键词
标签推荐/多标签分类/文本特征/公共文化资源
Key words
label recommendation/multi-label classification/text features/public cultural resources
维普
万方数据