Multi-label classification of research articles using Word2Vec and identification of similarity threshold
文献类型：期刊论文
| 作者 | Mustafa, Ghulam6; Usman, Muhammad5; Yu, Lisu3,4; Afzal, Muhammad Tanvir1; Sulaiman, Muhammad6; Shahid, Abdul2 |
| 刊名 | SCIENTIFIC REPORTS
 |
| 出版日期 | 2021-11-09 |
| 卷号 | 11期号:1页码:20 |
| ISSN号 | 2045-2322 |
| DOI | 10.1038/s41598-021-01460-7 |
| 英文摘要 | Every year, around 28,100 journals publish 2.5 million research publications. Search engines, digital libraries, and citation indexes are used extensively to search these publications. When a user submits a query, it generates a large number of documents among which just a few are relevant. Due to inadequate indexing, the resultant documents are largely unstructured. Publicly known systems mostly index the research papers using keywords rather than using subject hierarchy. Numerous methods reported for performing single-label classification (SLC) or multi-label classification (MLC) are based on content and metadata features. Content-based techniques offer higher outcomes due to the extreme richness of features. But the drawback of content-based techniques is the unavailability of full text in most cases. The use of metadata-based parameters, such as title, keywords, and general terms, acts as an alternative to content. However, existing metadata-based techniques indicate low accuracy due to the use of traditional statistical measures to express textual properties in quantitative form, such as BOW, TF, and TFIDF. These measures may not establish the semantic context of the words. The existing MLC techniques require a specified threshold value to map articles into predetermined categories for which domain knowledge is necessary. The objective of this paper is to get over the limitations of SLC and MLC techniques. To capture the semantic and contextual information of words, the suggested approach leverages the Word2Vec paradigm for textual representation. The suggested model determines threshold values using rigorous data analysis, obviating the necessity for domain expertise. Experimentation is carried out on two datasets from the field of computer science (JUCS and ACM). In comparison to current state-of-the-art methodologies, the proposed model performed well. Experiments yielded average accuracy of 0.86 and 0.84 for JUCS and ACM for SLC, and 0.81 and 0.80 for JUCS and ACM for MLC. On both datasets, the proposed SLC model improved the accuracy up to 4%, while the proposed MLC model increased the accuracy up to 3%. |
| 资助项目 | National Science Foundation of China (NSFC)[62161024] ; China Postdoctoral Science Foundation[2021TQ0136] ; State Key Laboratory of Computer Architecture (ICT, CAS) Open Project[CARCHB202019] |
| WOS研究方向 | Science & Technology - Other Topics |
| 语种 | 英语 |
| WOS记录号 | WOS:000716666700024 |
| 出版者 | NATURE PORTFOLIO |
| 源URL | [http://119.78.100.204/handle/2XEOYT63/18051]  |
| 专题 | 中国科学院计算技术研究所期刊论文_英文 |
| 通讯作者 | Yu, Lisu |
| 作者单位 | 1.Namal Inst, Dept Comp Sci, Islamabad 42200, Pakistan 2.Kohat Univ Sci & Technol, Inst Comp, Kohat 26000, Pakistan 3.Chinese Acad Sci, Inst Comp Technol, State Key Lab Comp Architecture, Beijing 100190, Peoples R China 4.Nanchang Univ, Sch Informat Engn, Nanchang 330031, Jiangxi, Peoples R China 5.Natl Univ Comp & Emerging Sci FAST, Dept Comp Sci, Islamabad 44000, Pakistan 6.Capital Univ Sci & Technol, Dept Comp Sci, Islamabad 44000, Pakistan |
| 推荐引用方式 GB/T 7714 | Mustafa, Ghulam,Usman, Muhammad,Yu, Lisu,et al. Multi-label classification of research articles using Word2Vec and identification of similarity threshold[J]. SCIENTIFIC REPORTS,2021,11(1):20. |
| APA | Mustafa, Ghulam,Usman, Muhammad,Yu, Lisu,Afzal, Muhammad Tanvir,Sulaiman, Muhammad,&Shahid, Abdul.(2021).Multi-label classification of research articles using Word2Vec and identification of similarity threshold.SCIENTIFIC REPORTS,11(1),20. |
| MLA | Mustafa, Ghulam,et al."Multi-label classification of research articles using Word2Vec and identification of similarity threshold".SCIENTIFIC REPORTS 11.1(2021):20. |
入库方式： OAI收割
来源：计算技术研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。