Multi-label classification of research articles using Word2Vec and identification of similarity threshold

Abstract 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....

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Ghulam Mustafa, Muhammad Usman, Lisu Yu, Muhammad Tanvir afzal, Muhammad Sulaiman, Abdul Shahid
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/b9fd15ad9772474f8fdd5d7654675975
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:b9fd15ad9772474f8fdd5d7654675975
record_format	dspace
spelling	oai:doaj.org-article:b9fd15ad9772474f8fdd5d76546759752021-11-14T12:20:37ZMulti-label classification of research articles using Word2Vec and identification of similarity threshold10.1038/s41598-021-01460-72045-2322https://doaj.org/article/b9fd15ad9772474f8fdd5d76546759752021-11-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-01460-7https://doaj.org/toc/2045-2322Abstract 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%.Ghulam MustafaMuhammad UsmanLisu YuMuhammad Tanvir afzalMuhammad SulaimanAbdul ShahidNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-20 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Ghulam Mustafa Muhammad Usman Lisu Yu Muhammad Tanvir afzal Muhammad Sulaiman Abdul Shahid Multi-label classification of research articles using Word2Vec and identification of similarity threshold
description	Abstract 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%.
format	article
author	Ghulam Mustafa Muhammad Usman Lisu Yu Muhammad Tanvir afzal Muhammad Sulaiman Abdul Shahid
author_facet	Ghulam Mustafa Muhammad Usman Lisu Yu Muhammad Tanvir afzal Muhammad Sulaiman Abdul Shahid
author_sort	Ghulam Mustafa
title	Multi-label classification of research articles using Word2Vec and identification of similarity threshold
title_short	Multi-label classification of research articles using Word2Vec and identification of similarity threshold
title_full	Multi-label classification of research articles using Word2Vec and identification of similarity threshold
title_fullStr	Multi-label classification of research articles using Word2Vec and identification of similarity threshold
title_full_unstemmed	Multi-label classification of research articles using Word2Vec and identification of similarity threshold
title_sort	multi-label classification of research articles using word2vec and identification of similarity threshold
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/b9fd15ad9772474f8fdd5d7654675975
work_keys_str_mv	AT ghulammustafa multilabelclassificationofresearcharticlesusingword2vecandidentificationofsimilaritythreshold AT muhammadusman multilabelclassificationofresearcharticlesusingword2vecandidentificationofsimilaritythreshold AT lisuyu multilabelclassificationofresearcharticlesusingword2vecandidentificationofsimilaritythreshold AT muhammadtanvirafzal multilabelclassificationofresearcharticlesusingword2vecandidentificationofsimilaritythreshold AT muhammadsulaiman multilabelclassificationofresearcharticlesusingword2vecandidentificationofsimilaritythreshold AT abdulshahid multilabelclassificationofresearcharticlesusingword2vecandidentificationofsimilaritythreshold
_version_	1718429310567579648

Multi-label classification of research articles using Word2Vec and identification of similarity threshold

Ejemplares similares