发表机构
MDPI（MDPI出版集团）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
SCALE是结合LLMs与嵌入的框架，在OpenAlex分类体系主题下新增科学概念层，将语义相关关键词组织为概念单元，为细粒度学术分类等提供基础。
AI 中文摘要
科研领域日益细分，对现有分类体系构成挑战——现有体系能有效表征广泛学科与研究主题，但常无法捕捉当代科学的细粒度概念结构。作者关键词虽具更高特异性，但其碎片化、冗余性及术语变异性，限制了作为稳定知识组织单元的应用。我们提出SCALE（Scientific Concept Aggregation via LLMs and Embeddings）框架，该框架在OpenAlex分类体系的主题（Topics）之下新增一层科学概念（Concepts）。SCALE不将关键词视为孤立描述符，而是将语义相关术语组织为连贯且可解释的概念单元，并将其整合至现有学科层级中。该框架结合科学文本嵌入、大语言模型及基于图的社区检测技术，规模化构建这一额外层级。最终形成的分类体系可让科研文献通过介于广泛研究主题与单篇文献之间的中间概念层级进行解读，该视角能更细致地表征科学知识的结构、细分及跨学科关联方式。通过将异构作者术语转化为可复用的层级单元，SCALE为细粒度学术分类、科学计量分析、研究监测及未来本体开发提供了基础。
英文摘要
The increasing specialization of scientific research challenges existing classification systems, which provide effective representations of broad disciplines and research topics but often fail to capture the fine-grained conceptual structure of contemporary science. Author keywords offer greater specificity, but their fragmentation, redundancy, and terminological variability limit their use as stable units of knowledge organization. We introduce SCALE (Scientific Concept Aggregation via LLMs and Embeddings), a framework that extends the OpenAlex taxonomy with a new level of scientific Concepts below Topics. Rather than treating keywords as isolated descriptors, SCALE organizes semantically related terms into coherent and interpretable conceptual units and integrates them within the existing disciplinary hierarchy. The framework combines scientific text embeddings, large language models, and graph-based community detection to construct this additional layer at scale. The resulting taxonomy enables scientific literature to be read through an intermediate conceptual level between broad research topics and individual documents. This perspective provides a more detailed representation of how scientific knowledge is structured, specialized, and connected across disciplines. By transforming heterogeneous author terminology into reusable hierarchical units, SCALE offers a foundation for fine-grained scholarly classification, scientometric analysis, research monitoring, and future ontology development.
Comments14 pages, 5 figures
