Automatically Cataloging Scholarly Articles using Library of Congress Subject Headings

Abstract

Institutes are required to catalog their articles with proper subject headings so that the users can easily retrieve relevant articles from the institutional repositories. However, due to the rate of proliferation of the number of articles in these repositories, it is becoming a challenge to manually catalog the newly added articles at the same pace. To address this challenge, we explore the feasibility of automatically annotating articles with Library of Congress Subject Headings (LCSH). We first use web scraping to extract keywords for a collection of articles from the Repository Analytics and Metrics Portal (RAMP). Then, we map these keywords to LCSH names for developing a goldstandard dataset. As a case study, using the subset of Biology-related LCSH concepts, we develop predictive models by formulating this task as a multi-label classification problem. Our experimental results demonstrate the viability of this approach for predicting LCSH for scholarly articles.

Research on the Automatic Subject-Indexing Method of Academic Papers Based on Climate Change Domain Ontology

“…Wartena and Franke-Maier (2018) studied the possibility of assigning LCSH automatically by training classifiers for terms used frequently in a large collection of abstracts of the literature on hand and by extracting headings from those abstracts by combining both methods [17]. Kazi et al (2021) use web-scraping techniques to extract keywords from article sets in the Literature Analysis and Metrics Portal, and map these keywords to biologically relevant LCSH names to develop a gold standard dataset that demonstrates the feasibility of this approach for predicting LCSH of scholarly articles [10].…”

“…However, LDA tends to produce noisier and difficult-to-interpret results, and its parameter specification setting is also a significant problem. Other state-of-the-art approaches either classify papers in a top-down fashion, taking advantage of pre-existent categories from domain vocabularies, such as Medical Subject Headings (MeSH), and Library of Congress Subject Headings (LCSH) [9,10]. The advantage of this method is that it relies on a set of artificially predefined research subject vocabularies and then uses trained machine learning classifiers to transform the labels of the nearest neighbors into predicted terms.…”