Automated text categorization of bibliographic records

2013

Library classification is a system which could classify both printed and non-printed sources in a library or information center with the prime intension of organizing those sources in a most helpful order to assist library users and library staff to find and to locate them efficiently and effectively. The intension of this paper is to study the different steps related to design and construction of a library classification system. A classificationist or an editorial committee of a library classification system has the responsibility and the ownership of design, construction and maintenance of a system. The objectives of this study are:

Subject terms play a crucial role in resource discovery but require substantial effort to produce. Automatic subject classification and indexing address problems of scale and sustainability and can be used to enrich existing bibliographic records, establish more connections across and between resources, and enhance consistency of bibliographic data. The paper aims to put forward a complex methodological framework to evaluate automatic classification tools of Swedish textual documents based on the Dewey Decimal Classification (DDC) recently introduced to Swedish libraries. Three major complementary approaches are suggested: a quality-built gold standard, retrieval effects, domain analysis. The gold standard is built based on input from at least two catalogue librarians, end users expert in the subject, end users inexperienced in the subject, and automated tools. Retrieval effects are studied through a combination of assigned and free tasks, including factual and comprehensive types. The study also takes into consideration the different role and character of subject terms in various knowledge domains, such as scientific disciplines. As a theoretical framework, domain analysis is used and applied in relation to the implementation of DDC in Swedish libraries and chosen domains of knowledge within the DDC itself.

This proposed new classification scheme is based on two main elements: hierarchism and binary theory. Hence, it is called Universal Binary Classification (UBC). Some advantages of this classification are highlighted including subject heading development, construction of a thesaurus, and all terms with meaningful features arranged in tabular form that can help researchers, through a semantic process, to find what they need. This classification scheme is fully consistent with the classification of knowledge. The classification of knowledge is also based on hierarchism and binary principle. Finally, a survey on randomly selected books in McLennan Library of McGill University is presented to compare the codes of this new classification with the currently employed Library of Congress Classification (LCC) numbers in the discipline of Library and Information Sciences.

Journal of documentation, 2024

Purpose -In 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/approach -On 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. Findings -The 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/value -The 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.

Journal of Information Science Theory and Practice, 2015

This paper describes qualities of a library classification system that are commonly discussed in the LIS tradition and literature, and explains such a system's three main functions, namely knowledge mapping, information retrieval, and shelf arrangement. In this vein, the paper states the functional requirements of bibliographic classifications, which broadly are subject collocation and facilitation of browsing the collection. It explains with details the components of a library classification system and their functions. The major components are schedules, notations, and index. It also states their distinguished features, such as generalia class, form divisions, book numbers, and devices for number synthesis which are not required in a knowledge classification. It illustrates with examples from the WebDewey good examples of added features of an online library classification system. It emphasizes that institutional backup and a revision machinery are essential for a classification to survive and remain relevant in the print and e-environment.

Library Resources & Technical Services, 2010

for her help in improving the manuscript. S peculations, questions, anxieties, and excitement about the roles and pos- sible futures of cataloging and catalogers underlie much of the literature of cataloging and classification during 2007-8. While many publications focused on the future and the significant changes that emerging trends may require, other contributions addressed a variety of aspects of practice-many immediate and practical-and underlying philosophy. Topics in the history of bibliographic control and in representing diverse and global perspectives in cataloging data also were strongly in evidence. The objectives of this paper are to • survey the extensive and varied literature of cataloging and classification during 2007-8; • indicate the range of this literature in terms of types of publications, including scholarly works but also publications intended to aid practitioners and communicate cataloging issues to noncatalogers; • identify major subject areas and themes; and • recommend substantive contributions in these areas, along with more ephemeral but worthy contributions useful to catalogers struggling to keep cataloging alive and useful in a period of scrutiny, uncertainty, multiple initiatives, and change. Using a bibliographic management program, we began the project by creating a database of citations with folders for 2007 and 2008. To do this, we searched several online databases, including Library Literature and Information Science Full Text; Library, Information Science, and Technology Abstracts with Full Text; Online Computer Library Center (OCLC) WorldCat; and Dissertations and Theses Online. Search strategies included both keyword and subject heading searches, using many pertinent terms, such as bibliographic control, cataloging, Review of the Literature 2007-8 By Sydney Chambers and Carolynne Myall This paper surveys library literature on cataloging and classification published in 2007-8, indicating its extent and range in terms of types of literature, major subject areas, and themes. The paper reviews pertinent literature in the following areas: the future of bibliographic control, general cataloging standards and texts, Functional Requirements for Bibliographic Records (FRBR), cataloging varied resources, metadata and cataloging in the Web world, classification and subject access, questions of diversity and diverse perspectives, additional reports of practice and research, catalogers' education and careers, keeping current through columns and blogs, and cataloging history.