Assessing Network Representations for Identifying Interdisciplinarity

TL;DR

This paper investigates how graph learning methods can generate embedded representations of research papers in citation networks to identify interdisciplinarity without relying on predefined disciplinary categories.

Contribution

It demonstrates that graph representations preserving structural equivalence excel at predicting interdisciplinary citations, offering a new approach to assess research interdisciplinarity.

Findings

Representations preserving structural equivalence improve interdisciplinary citation prediction.

Graph learning methods can encode interdisciplinarity without disciplinary categories.

Structural equivalence-based embeddings outperform other methods in identifying interdisciplinary research.

Abstract

Many studies have sought to identify interdisciplinary research as a function of the diversity of disciplines identified in an article's references or citations. However, given the constant evolution of the scientific landscape, disciplinary boundaries are shifting and blurring, making it increasingly difficult to describe research within a strict taxonomy. In this work, we explore the potential for graph learning methods to learn embedded representations for research papers that encode their 'interdisciplinarity' in a citation network. This facilitates the identification of interdisciplinary research without the use of disciplinary categories. We evaluate these representations and their ability to identify interdisciplinary research, according to their utility in interdisciplinary citation prediction. We find that those representations which preserve structural equivalence in the citation graph are best able to predict distant, interdisciplinary interactions in the network, according to multiple definitions of citation distance.