• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to project page

2020 Fiscal Year Final Research Report

Representation learning from multiple heterogeneous graph using scholarly big data

Research Project

  • PDF
Project/Area Number 17K00427
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Research Field Web informatics, Service informatics
Research InstitutionThe University of Tokyo

Principal Investigator

Mori Junichiro  東京大学, 大学院情報理工学系研究科, 准教授 (30508924)

Project Period (FY) 2017-04-01 – 2021-03-31
Keywords学術文献データ / 引用ネットワーク / 表現学習
Outline of Final Research Achievements

In this study, we propose the method for representation learning from multiple heterogeneous network data in order to support the extraction and discovery of useful knowledge from large-scale scholarly data. We develop the system for large-scale scholarly data analysis. In particular, we conducted citation network analysis on a large dataset of academic literature on COVID-19 using the Academic Industry and Technology Overview System, which is one of our research results, and extracted information on scientific evidence and important technologies related to COVID-19. The results of the analysis have been widely available to the public in order to support evidence-based approaches to COVID-19. The results of these studies have been published in several international conferences and journals.

Free Research Field

人工知能

Academic Significance and Societal Importance of the Research Achievements

本研究では、大規模な論文データから生成される複数の異種ネットワークから適切な分散表現学習をする手法の知見を明らかにした。また、学習されたネットワーク分散表現を論文データ分析における複数のタスクに適用しその有効性を明らかにした。その上で、実際に大規模論文データ分析のシステム構築を行い、政策立案者、研究者、データベースプロバイダなど科学技術の複数のステークホルダの視点から、ネットワークデータを大規模な学術文献情報からの知識発見に利活用するための知見を明らかにした。

URL: 

Published: 2022-01-27  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi