Mapping the Web of Science, a large-scale graph and text-based dataset with LLM embeddings

2026-02-04

AI Summary

This study addresses the challenge of effectively integrating textual semantics and citation network structure to uncover the intrinsic organizational principles of large-scale scholarly publications. Leveraging the Web of Science dataset comprising 56 million papers, the work presents the first systematic integration of large language model (LLM)-derived text embeddings with citation graph topology to construct a unified semantic–structural knowledge graph. By establishing a coherent representation of multimodal heterogeneous data, the approach reveals natural disciplinary clusters and cross-domain linkage patterns, elucidating a self-organizing knowledge landscape shaped jointly by semantic content and citation relationships. This framework establishes a novel paradigm for knowledge discovery in ultra-large-scale academic corpora.

Technology Category

• Data Mining & Knowledge Management: Semantic Web
• Natural Language Processing: Sentence-level Semantics, Textual Inference, etc.
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Bridging structured and unstructured data

Abstract

Large text data sets, such as publications, websites, and other text-based media, inherit two distinct types of features: (1) the text itself, its information conveyed through semantics, and (2) its relationship to other texts through links, references, or shared attributes. While the latter can be described as a graph structure and can be handled by a range of established algorithms for classification and prediction, the former has recently gained new potential through the use of LLM embedding models. Demonstrating these possibilities and their practicability, we investigate the Web of Science dataset, containing ~56 million scientific publications through the lens of our proposed embedding method, revealing a self-structured landscape of texts.

Problem

• text embeddings
• graph structure
• semantic information
• scientific publications
• large-scale dataset

Innovation

• LLM embeddings
• graph-text integration
• Web of Science
• semantic structure
• large-scale scientific data