Periodical embeddings uncover hidden interdisciplinary patterns in the subject classification scheme of science

2025-12-27

AI Summary

Existing disciplinary classification systems (e.g., Scopus) suffer from coarse granularity and strong subjectivity, limiting their ability to capture emerging interdisciplinary dynamics; moreover, citation-based approaches lack semantic validation. To address these limitations, we propose Periodical2Vec (P2V), a journal embedding method trained on citation relations across 23 million papers. P2V is the first to enable quantitative evaluation of scientific classification systems via an abstract semantic categorization task. Integrating k-means clustering with text classification frameworks, it uncovers evolutionary patterns of disciplinary “splitting and merging” and identifies latent interdisciplinary clusters—such as Biomedical Engineering—overlooked by conventional taxonomies. Experiments demonstrate that P2V significantly outperforms Scopus and state-of-the-art citation- and graph-embedding baselines in classification accuracy, precisely delineating fine-grained domains (e.g., Oncology, Cardiology) and interdisciplinary communities.

Technology Category

• Data Mining & Knowledge Management: Semantic Web
• Application Domains: Humanities & Computational Social Science
• Natural Language Processing: Discourse, Pragmatics & Argument Mining

Application Category

• Web Mining and Content Analysis: Interdisciplinary science discovery with web data mining
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

Subject classification schemes are foundational to the organization, evaluation, and navigation of scientific knowledge. While expert-curated systems like Scopus provide widely used taxonomies, they often suffer from coarse granularity, subjectivity, and limited adaptability to emerging interdisciplinary fields. Data-driven alternatives based on citation networks show promise but lack rigorous, external validation against the semantic content of scientific literature. Here, we propose a novel quantitative framework that leverages classification tasks to evaluate the effectiveness of journal classification schemes. Using over 23 million paper abstracts, we demonstrate that labels derived from k-means clustering on Periodical2Vec (P2V)--a periodical embedding learned from paper-level citations--yield significantly higher classification performance than both Scopus and other data-driven baselines (e.g., citation, co-citation, and Node2Vec variants). By comparing journal partitions across classification schemes, two structural patterns emerge on the map of science: (1) the reorganization of disciplinary boundaries--splitting overly broad categories (e.g., "Medicine" into "Oncology", "Cardiology", and other specialties) while merging artificially fragmented ones (e.g., "Chemistry" and "Chemical Engineering"); and (2) the identification of coherent interdisciplinary clusters--such as "Biomedical Engineering", "Medical Ethics", and "Information Management"--that are dispersed across multiple categories but unified in citation space. These findings underscore that citation-derived periodical embeddings not only outperform traditional taxonomies in predictive validity but also offer a dynamic, fine-grained map of science that better reflects both the specialization and interdisciplinarity inherent in contemporary research.

Problem

• Evaluating effectiveness of journal classification schemes using classification tasks
• Comparing journal partitions to reveal structural patterns in science
• Identifying interdisciplinary clusters dispersed across traditional categories

Innovation

• Periodical2Vec embeddings from citation data
• K-means clustering for journal classification
• Dynamic fine-grained map of science