基于词向量的npm包推荐标签方法

吉林大学学报(理学版) ›› 2022, Vol. 60 ›› Issue (5): 1097-1102.

基于词向量的npm包推荐标签方法

孙凯¹, 刘宣彤², 张莉³, 刘华虓¹, 王禹¹, 郜山权¹

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

收稿日期:2021-06-12 出版日期:2022-09-26 发布日期:2022-09-26
通讯作者: 张莉 E-mail:zh_li7213@163.com

Recommended Tag Method for npm Packages Based on Word Vector

SUN Kai¹, LIU Xuantong², ZHANG Li³, LIU Huaxiao¹, WANG Yu¹, GAO Shanquan¹

1. College of Computer Science and Technology, Jilin University, Changchun 130012， China;
2. Department of English, China Foreign Affairs University, Beijing 100037, China;
3. College of Information Technology, Baicheng Medical College, Baicheng 137000, Jilin Province, China

Received:2021-06-12 Online:2022-09-26 Published:2022-09-26

摘要/Abstract

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eadme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%.

关键词: 标签推荐, npm包, 词向量

Abstract: 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%.

Key words: tag recommendation, npm package, word vector

中图分类号:

TP311

孙凯, 刘宣彤, 张莉, 刘华虓, 王禹, 郜山权. 基于词向量的npm包推荐标签方法[J]. 吉林大学学报(理学版), 2022, 60(5): 1097-1102.

SUN Kai, LIU Xuantong, ZHANG Li, LIU Huaxiao, WANG Yu, GAO Shanquan. Recommended Tag Method for npm Packages Based on Word Vector[J]. Journal of Jilin University Science Edition, 2022, 60(5): 1097-1102.

[1]	刘磊, 王昊, 孙凯, 郜山权, 刘宣彤. 基于seq2seq模型的标签推荐方法[J]. 吉林大学学报(理学版), 2022, 60(2): 316-320.
[2]	杨光, 贾焱鑫, 陈翔, 许舒源. 基于深度学习的Stack Overflow问题帖分类方法[J]. 吉林大学学报(理学版), 2021, 59(4): 922-928.
[3]	高云龙, 左万利, 王英, 王鑫. 基于集成神经网络的短文本分类模型[J]. 吉林大学学报(理学版), 2018, 56(4): 933-938.