基于词向量的npm包推荐标签方法  

Recommended Tag Method for npm Packages Based on Word Vector

作　　者：孙凯[1] 刘宣彤 张莉 刘华虓[1] 王禹 郜山权 SUN Kai;LIU Xuantong;ZHANG Li;LIU Huaxiao;WANG Yu;GAO Shanquan(College of Computer Science and Technology,Jilin University,Changchun 130012,China;Department of English,China Foreign Affairs University,Beijing 100037,China;College of Information Technology,Baicheng Medical College,Baicheng 137000,Jilin Province,China)

机构地区：[1]吉林大学计算机科学与技术学院,长春130012 [2]外交学院英语系,北京100037 [3]白城医学高等专科学校信息化学院,吉林白城137000

出　　处：《吉林大学学报（理学版）》2022年第5期1097-1102,共6页Journal of Jilin University:Science Edition

基　　金：吉林省自然科学基金(批准号:20190201193JC);吉林大学研究生创新基金(批准号:101832020CX181);吉林大学博士研究生跨学科研究项目(批准号:101832020DJX064)。

摘　　要：针对开源npm(node package manager)社区标签机制不完善的问题,提出一种自动为开源第三方库npm包推荐标签的方法.首先,根据npm社区中现有标签间的关联关系对标签聚类,在解决标签同义词问题的同时建立标签库;其次,利用词向量技术计算npm包的Readme文档与标签库中标签的语义相关程度;最后,根据相关程度对标签进行排序,生成标签推荐列表并完成标签推荐.实验结果表明,该方法可有效地为npm包推荐标签,准确率Recall@3为49.1%, Recall@5为56.3%, Recall@10为66.9%.Aiming at the problem of the imperfect tagging mechanism in the open source npm(node package manager) community, we proposed a method to automatically recommend tags for open source third-party library npm packages. Firstly, according to the association relationship between existing tags in the npm community, the tags were clustered and a tag library was established while solving the problem of tag synonyms. Secondly, the word vector technology was used to calculate the semantic correlation degree between the Readme document of the npm package and the tags in the tag library. Finally, the tags were sorted according to the degree of correlation to generate a tag recommendation list and complete the tag recommendation. The experimental results show that this method can effectively recommend tags for npm packages, and the accuracy rate of Recall@3 is 49.1%, Recall@5 is 56.3%, and Recall@10 is 66.9%.

关 键 词：标签推荐 npm包 词向量 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]