MARC

LEADER 00000nab a2200000uu 4500
001 3098984157
003 UK-CbPIL
022 |a 0022-0418 
022 |a 1758-7379 
024 7 |a 10.1108/JD-01-2022-0026  |2 doi 
035 |a 3098984157 
045 2 |b d20240901  |b d20241031 
084 |a 38173  |2 nlm 
100 1 |a Golub, Koraljka  |u iInstitute, Linnaeus University, Vaxjo, Sweden 
245 1 |a Automated Dewey Decimal Classification of Swedish library metadata using Annif software 
260 |b Emerald Group Publishing Limited  |c 2024 
513 |a Journal Article 
520 3 |a 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. 
610 4 |a Online Computer Library Center--OCLC National Library of Medicine 
653 |a Text categorization 
653 |a Software 
653 |a Accuracy 
653 |a Metadata 
653 |a Classification 
653 |a Information retrieval 
653 |a Information professionals 
653 |a Subject heading schemes 
653 |a Automation 
653 |a Library of Congress Subject Headings 
653 |a Open source software 
653 |a Library catalogs 
653 |a Software packages 
653 |a Qualitative analysis 
653 |a Machine learning 
653 |a Subject indexing 
653 |a National libraries 
653 |a Neural networks 
653 |a Support vector machines 
653 |a Algorithms 
653 |a Indexing 
653 |a Dewey Decimal Classification 
653 |a Catalogs 
653 |a Documents 
653 |a Libraries 
653 |a Data mining 
653 |a Archives & records 
653 |a Agreements 
653 |a Property 
653 |a Catalogues 
653 |a Classifiers 
653 |a Copyright 
653 |a Swedish language 
653 |a Information 
653 |a Qualitative research 
653 |a Retrieval 
653 |a Librarians 
653 |a Supervision 
653 |a Government Libraries 
653 |a Computers 
653 |a Library Networks 
653 |a Computer Interfaces 
653 |a Numbers 
653 |a Artificial Intelligence 
653 |a Computational Linguistics 
653 |a International Organizations 
700 1 |a Suominen, Osma  |u Library Network Services, The National Library of Finland, Helsinki, Finland 
700 1 |a Ahmed Taiye Mohammed  |u iInstitute, Linnaeus University, Vaxjo, Sweden 
700 1 |a Aagaard, Harriet  |u National Library of Sweden, Stockholm, Sweden 
700 1 |a Osterman, Olof  |u National Library of Sweden, Stockholm, Sweden 
773 0 |t Journal of Documentation  |g vol. 80, no. 5 (2024), p. 1057-1079 
786 0 |d ProQuest  |t ABI/INFORM Global 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3098984157/abstract/embedded/L8HZQI7Z43R0LA5T?source=fedsrch 
856 4 0 |3 Full Text  |u https://www.proquest.com/docview/3098984157/fulltext/embedded/L8HZQI7Z43R0LA5T?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3098984157/fulltextPDF/embedded/L8HZQI7Z43R0LA5T?source=fedsrch