Hierarchical Classification of Research Fields in the "Web of Science" Using Deep Learning

TL;DR

This paper introduces a hierarchical deep learning-based classification system that automatically categorizes scholarly abstracts into disciplines, fields, and subfields, achieving over 90% accuracy and supporting interdisciplinary research analysis.

Contribution

It presents a novel multi-level classification framework using deep learning models trained on a large scholarly dataset, enabling automated, accurate, and interdisciplinary categorization of research publications.

Findings

Classification accuracy exceeds 90% in most cases

Supports multi-label and interdisciplinary classification

Enables automated indexing of scientific publications

Abstract

This paper presents a hierarchical classification system that automatically categorizes a scholarly publication using its abstract into a three-tier hierarchical label set (discipline, field, subfield) in a multi-class setting. This system enables a holistic categorization of research activities in the mentioned hierarchy in terms of knowledge production through articles and impact through citations, permitting those activities to fall into multiple categories. The classification system distinguishes 44 disciplines, 718 fields and 1,485 subfields among 160 million abstract snippets in Microsoft Academic Graph (version 2018-05-17). We used batch training in a modularized and distributed fashion to address and allow for interdisciplinary and interfield classifications in single-label and multi-label settings. In total, we have conducted 3,140 experiments in all considered models (Convolutional Neural Networks, Recurrent Neural Networks, Transformers). The classification accuracy is > 90% in 77.13% and 78.19% of the single-label and multi-label classifications, respectively. We examine the advantages of our classification by its ability to better align research texts and output with disciplines, to adequately classify them in an automated way, and to capture the degree of interdisciplinarity. The proposed system (a set of pre-trained models) can serve as a backbone to an interactive system for indexing scientific publications in the future.