EUVIMEDEUVIMED entdecken
Crossref

Deep representation learning of scientific paper reveals its potential scholarly impact

Zhuoren Jiang, Tianqianjin Lin, Cui Huang

Journal of Informetrics · 2023-02 · 17 (1) · 101376

DOI: 10.1016/j.joi.2023.101376 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Informetrics, 2023-02. Verfasst von Zhuoren Jiang und 2 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 82 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Zhejiang Province, Fundamental Research Funds for the Central Universities.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Citation and citation-based metrics are traditionally used to quantify the scholarly impact of scientific papers. However, for documents without citation data, i.e., newly published papers, the citation-based metrics are not available. By leveraging deep representation techniques, we propose a text-content based approach that may reveal the scholarly impact of papers without human domain-specific knowledge. Specifically, a large-scale Pre-Trained Model (PTM) with 110 million parameters is utilized to automatically encode the paper into the vector representation. Two indicators, τ (Topicality) and σ (Originality), are then proposed based on the learned representations. These two indicators leverage the spatial relations of paper representations in the semantic space to capture the impact-related characteristics of a scientific paper. Extensive experiments have been conducted on a COVID-19 open research dataset with 1,056,660 papers. The experimental results demonstrate that the deep representation learning method can better capture the scientific content in the published literature;and the proposed indicators are positively and significantly associated with a paper's potential scholarly impact. In the multivariate regression analysis for the potential impact of a paper, the coefficients of σ and τ are 5.4915 (P

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Zhejiang Province
  • Fundamental Research Funds for the Central Universities

Zitieren

APA

Jiang, Z., Lin, T., & Huang, C. (2023). Deep representation learning of scientific paper reveals its potential scholarly impact. Journal of Informetrics, 17(1), 101376. https://doi.org/10.1016/j.joi.2023.101376

Vancouver

Jiang Z, Lin T, Huang C. Deep representation learning of scientific paper reveals its potential scholarly impact. Journal of Informetrics. 2023;17(1):101376. doi:10.1016/j.joi.2023.101376

BibTeX
@article{Jiang2023,
  author = {Jiang, Zhuoren and Lin, Tianqianjin and Huang, Cui},
  title = {Deep representation learning of scientific paper reveals its potential scholarly impact},
  journal = {Journal of Informetrics},
  year = {2023},
  volume = {17},
  number = {1},
  pages = {101376},
  doi = {10.1016/j.joi.2023.101376}
}
Kostenlos starten →