Scholarlink

<p>Arboviruses represent a critical area of research in the field of infectious diseases, necessitating systematic and comprehensive analysis to extract actionable insights. This study introduces an AI-driven knowledge-data graph (KDG) that provides novel perspectives on the global arbovirus research landscape. The KDG comprehensively covers the meaningful research directions and their fine-grained subdivisions organized in a hierarchical structure. We have involved human experts in interacting with a generic large language model (LLM) for constructing the hierarchical topic structure of the overall arbovirus research, forming the basis of KDG for AI-driven meta-analysis of the research area. We then pre-trained a domain-specific language model, ArboBERT, specifically tailored for arbovirus, to establish the knowledge-data association in a low-resource, high-efficiency, and high-accuracy fashion to enable the integration of the structural and statistical analysis. We further extracted key entities such as researchers, institutes, journals, geographical entities, time, and virus species to form KDG at a deeper level of the topic hierarchy, allowing for more nuanced insights and a better understanding of the complex relationships within the field. This AI-driven KDG enables perspectives from people-related, temporal, geographical, and interactive views, facilitating dynamic, comprehensive, and in-depth analysis and insights into global arbovirus research.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

AI-driven knowledge-data graph for tracking global arbovirus research

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年9月24日

查看全文
  • Zhaoyan Ming,
  • Ying Huang,
  • Cheng Hu,
  • Jiahao Peng,
  • Weijun Sun,
  • Weijin Guo,
  • Tang Sheng,
  • Xiangyu Huangfu,
  • Zhaolin Li,
  • Xinrui Li,
  • Jicheng Huang,
  • Zhiming Yuan,
  • Guanlin Chen,
  • Kui Su,
  • Yongxia Shi,
  • Han Xia

摘要

Arboviruses represent a critical area of research in the field of infectious diseases, necessitating systematic and comprehensive analysis to extract actionable insights. This study introduces an AI-driven knowledge-data graph (KDG) that provides novel perspectives on the global arbovirus research landscape. The KDG comprehensively covers the meaningful research directions and their fine-grained subdivisions organized in a hierarchical structure. We have involved human experts in interacting with a generic large language model (LLM) for constructing the hierarchical topic structure of the overall arbovirus research, forming the basis of KDG for AI-driven meta-analysis of the research area. We then pre-trained a domain-specific language model, ArboBERT, specifically tailored for arbovirus, to establish the knowledge-data association in a low-resource, high-efficiency, and high-accuracy fashion to enable the integration of the structural and statistical analysis. We further extracted key entities such as researchers, institutes, journals, geographical entities, time, and virus species to form KDG at a deeper level of the topic hierarchy, allowing for more nuanced insights and a better understanding of the complex relationships within the field. This AI-driven KDG enables perspectives from people-related, temporal, geographical, and interactive views, facilitating dynamic, comprehensive, and in-depth analysis and insights into global arbovirus research.