Automated Dewey Decimal Classification of Swedish library metadata using Annif software

• Published in: Journal of documentation Vol. 80; no. 5; pp. 1057 - 1079
• Main Authors: Golub, Koraljka, Suominen, Osma, Mohammed, Ahmed Taiye, Aagaard, Harriet, Osterman, Olof
• Format: Journal Article
• Language: English
• Published: Bradford Emerald Publishing Limited 03.09.2024; Emerald Group Publishing Limited
• Subjects: Accuracy; Algorithms; Annif; Artificial Intelligence; Automated subject indexing; Automatic classification; Automation; Biblioteks- och informationsvetenskap; Classification; Computational Linguistics; Computer Interfaces; Computers; DDC; Dewey Decimal Classification; Documents; Ensemble approach; Government Libraries; Indexing; Information professionals; Information retrieval; International Organizations; Lexical algorithm; Library and Information Science; Library catalogs; Library Networks; Library of Congress Subject Headings; Libris; Machine learning; Metadata; National libraries; Neural networks; Numbers; Open source software; Qualitative analysis; Qualitative evaluation; Software; Software packages; Subject heading schemes; Subject indexing; Supervised machine learning; Supervision; Support vector machines; Text categorization; Libris; Qualitative evaluation; Automatic classification; DDC; Supervised machine learning; Lexical algorithm; Ensemble approach; Annif; Automated subject indexing
• DOI: 10.1108/JD-01-2022-0026
• ISSN: 0022-0418; 1758-7379

PurposeIn order to estimate the value of semi-automated subject indexing in operative library catalogues, the study aimed to investigate five different automated implementations of an open source software package on a large set of Swedish union catalogue metadata records, with Dewey Decimal Classification (DDC) as the target classification system. It also aimed to contribute to the body of research on aboutness and related challenges in automated subject indexing and evaluation.Design/methodology/approachOn a sample of over 230,000 records with close to 12,000 distinct DDC classes, an open source tool Annif, developed by the National Library of Finland, was applied in the following implementations: lexical algorithm, support vector classifier, fastText, Omikuji Bonsai and an ensemble approach combing the former four. A qualitative study involving two senior catalogue librarians and three students of library and information studies was also conducted to investigate the value and inter-rater agreement of automatically assigned classes, on a sample of 60 records.FindingsThe best results were achieved using the ensemble approach that achieved 66.82% accuracy on the three-digit DDC classification task. The qualitative study confirmed earlier studies reporting low inter-rater agreement but also pointed to the potential value of automatically assigned classes as additional access points in information retrieval.Originality/valueThe paper presents an extensive study of automated classification in an operative library catalogue, accompanied by a qualitative study of automated classes. It demonstrates the value of applying semi-automated indexing in operative information retrieval systems.