lnu.sePublications
Change search
Link to record
Permanent link

Direct link
BETA
Publications (10 of 113) Show all publications
Golub, K., Hagelbäck, J. & Ardö, A. (2018). Automatic classification using DDC on the Swedish Union Catalogue. In: Philipp Mayr, Douglas Tudhope, Joseph Busch, Koraljka Golub, Marjorie Hlava & Marcia Zeng (Ed.), Proceedings of the 18th European Networked Knowledge Organization Systems (NKOS 2018) Workshop, Porto, Portugal, September 13, 2018: . Paper presented at 18th European Networked Knowledge Organization Systems Workshop (NKOS 2018), Porto, Portugal, September 13, 2018 (pp. 4-16). CEUR-WS.org
Open this publication in new window or tab >>Automatic classification using DDC on the Swedish Union Catalogue
2018 (English)In: Proceedings of the 18th European Networked Knowledge Organization Systems (NKOS 2018) Workshop, Porto, Portugal, September 13, 2018 / [ed] Philipp Mayr, Douglas Tudhope, Joseph Busch, Koraljka Golub, Marjorie Hlava & Marcia Zeng, CEUR-WS.org , 2018, p. 4-16Conference paper, Published paper (Refereed)
Abstract [en]

With more and more digital collections of various information re- sources becoming available, also increasing is the challenge of assigning subject index terms and classes from quality knowledge organization systems. While the ultimate purpose is to understand the value of automatically produced Dewey Decimal Classification (DDC) classes for Swedish digital collections, the paper aims to evaluate the performance of two machine learning algorithms for Swe- dish catalogue records from the Swedish union catalogue (LIBRIS). The algo- rithms are tested on the top three hierarchical levels of the DDC. Based on a data set of 143,838 records, evaluation shows that Support Vector Machine with linear kernel outperforms Multinomial Naïve Bayes algorithm. Also, using keywords or combining titles and keywords gives better results than using only titles as input. The class imbalance where many DDC classes only have few records greatly affects classification performance: 81.37% accuracy on the training set is achieved when at least 1,000 records per class are available, and 66.13% when few records on which to train are available. Proposed future research involves an exploration of the intellectual effort put into creating the DDC to further improve the algorithm performance as commonly applied in string matching, and to test the best approach on new digital collections that do not have DDC assigned.

Place, publisher, year, edition, pages
CEUR-WS.org, 2018
Series
CEUR Workshop Proceedings, ISSN 1613-0073 ; 2200
Keywords
LIBRIS, Dewey Decimal Classification, automatic classification, machine learning, Support Vector Machine, Multinomial Naïve Bayes, subject access
National Category
Information Studies
Research subject
Humanities, Library and Information Science
Identifiers
urn:nbn:se:lnu:diva-78378 (URN)
Conference
18th European Networked Knowledge Organization Systems Workshop (NKOS 2018), Porto, Portugal, September 13, 2018
Available from: 2018-10-19 Created: 2018-10-19 Last updated: 2018-10-19Bibliographically approved
Golub, K. (2018). [ Review of ] Tatjana Aparac-Jelušić : Digital Libraries for Cultural Heritage : Development, Outcomes, and Challenges from European Perspectives [Review]. Vjesnik Bibliotekara Hrvatske
Open this publication in new window or tab >>[ Review of ] Tatjana Aparac-Jelušić : Digital Libraries for Cultural Heritage : Development, Outcomes, and Challenges from European Perspectives
2018 (Croatian)In: Vjesnik Bibliotekara Hrvatske, ISSN 0507-1925, E-ISSN 1334-6938Article, book review (Other academic) Published
National Category
Information Studies
Research subject
Humanities, Library and Information Science
Identifiers
urn:nbn:se:lnu:diva-70800 (URN)
Available from: 2018-02-13 Created: 2018-02-13 Last updated: 2018-02-13
Golub, K. (2018). Subject Access in Swedish Discovery Services. Knowledge organization, 45(4), 297-309
Open this publication in new window or tab >>Subject Access in Swedish Discovery Services
2018 (English)In: Knowledge organization, ISSN 0943-7444, Vol. 45, no 4, p. 297-309Article in journal (Refereed) Published
Abstract [en]

While support for subject searching has been traditionally advocated for in library catalogs, often in the form of a catalog objective to find everything that a library has on a certain topic, research has shown that subject access has not been satisfactory. Many existing online catalogs and discovery services do not seem to make good use of the intellectual effort invested into assigning controlled subject index terms and classes. For example, few support hierarchical browsing of classification schemes and other controlled vocabularies with hierarchical structures, few provide end-user-friendly options to choose a more specific concept to increase precision, a broader concept or related concepts to increase recall, to disambiguate homonyms, or to find which term is best used to name a concept. Optimum subject access in library catalogs and discovery services is analyzed from the perspective of earlier research as well as contemporary conceptual models and cataloguing codes. Eighteen proposed features of what this should entail in practice are drawn. In an exploratory qualitative study, the three most common discovery services used in Swedish academic libraries are analyzed against these features. In line with previous research, subject access in contemporary interfaces is demonstrated to less than optimal. This is in spite of the fact that individual collections have been indexed with controlled vocabularies and a significant number of controlled vocabularies have been mapped to each other and are available in interoperable standards. Strategic action is proposed to build research-informed (inter)national standards and guidelines.

Place, publisher, year, edition, pages
Ergon-Verlag, 2018
Keywords
subject searching, subject access, discovery, controlled vocabularies, terms
National Category
Information Studies
Research subject
Humanities, Library and Information Science
Identifiers
urn:nbn:se:lnu:diva-77415 (URN)10.5771/0943-7444-2018-4-297 (DOI)000439042400004 ()
Available from: 2018-08-29 Created: 2018-08-29 Last updated: 2018-08-29Bibliographically approved
Golub, K. (2018). The Making of an iSchool. Information today, 35(4)
Open this publication in new window or tab >>The Making of an iSchool
2018 (English)In: Information today, ISSN 8755-6286, E-ISSN 2169-0340, Vol. 35, no 4Article, review/survey (Other academic) Published
National Category
Information Studies
Research subject
Humanities, Library and Information Science
Identifiers
urn:nbn:se:lnu:diva-74302 (URN)
Available from: 2018-05-09 Created: 2018-05-09 Last updated: 2018-06-20Bibliographically approved
Golub, K. (2017). A framework for evaluating automatic indexing or classification in the context of retrieval: invited talk. In: A Calculus of Culture : Circumventing the Black Box of Culture Analytics, Guangxi University, China, March 21-23, 2017: . Paper presented at A Calculus of Culture : Circumventing the Black Box of Culture Analytics, Guangxi University, China, March 21-23, 2017.
Open this publication in new window or tab >>A framework for evaluating automatic indexing or classification in the context of retrieval: invited talk
2017 (English)In: A Calculus of Culture : Circumventing the Black Box of Culture Analytics, Guangxi University, China, March 21-23, 2017, 2017Conference paper, Oral presentation only (Other academic)
National Category
Information Studies
Identifiers
urn:nbn:se:lnu:diva-62463 (URN)
Conference
A Calculus of Culture : Circumventing the Black Box of Culture Analytics, Guangxi University, China, March 21-23, 2017
Available from: 2017-04-13 Created: 2017-04-13 Last updated: 2017-05-24Bibliographically approved
Golub, K., Tyrkkö, J., Kerren, A., Jusufi, I. & Ardö, A. (2017). Automatic subject classification for improving retrieval in a Swedish repository. In: ISKO UK Conference 2017: Knowledge Organization: what's the story?, 11 – 12 September 2017, London: . Paper presented at ISKO UK Conference 2017: Knowledge Organization: what's the story?, 11 – 12 September 2017, London.
Open this publication in new window or tab >>Automatic subject classification for improving retrieval in a Swedish repository
Show others...
2017 (English)In: ISKO UK Conference 2017: Knowledge Organization: what's the story?, 11 – 12 September 2017, London, 2017Conference paper, Poster (with or without abstract) (Refereed)
Abstract [en]

The recent adoption of the Dewey Decimal Classification (DDC) in Sweden has ignited discussions about automated subject classification especially for digital collections, which generally seem to lack subject indexing from controlled vocabularies. This is particularly problematic in the context of academic resource retrieval tasks, which require an understanding of discipline-specific terminologies and the narratives behind their internal ontologies. The currently available experimental classification software have not been adequately tested and their usefulness is unproven especially for Swedish language resources. We address these issues by investigating a unifying framework of automatic subject indexing for the DDC, including an analysis of suitable interactive visualisation features for supporting these aims. We will address the disciplinary narratives behind the DDC in selected subject areas and the preliminary results will include an analysis of the data collection and a breakdown of the methodology. Major visualisation possibilities in support of the classification process are also outlined. The project will contribute significantly to Swedish information infrastructure by improving the findability of Swedish research resources by subject searching, one of the most common yet the most challenging types of searching.

National Category
Information Studies
Research subject
Computer Science, Information and software visualization
Identifiers
urn:nbn:se:lnu:diva-67925 (URN)
Conference
ISKO UK Conference 2017: Knowledge Organization: what's the story?, 11 – 12 September 2017, London
Projects
DISA-DH
Available from: 2017-09-12 Created: 2017-09-12 Last updated: 2018-01-10Bibliographically approved
Golub, K. (2017). Automatic subject indexing of text. In: Birger Hjørland, Claudio Gnoli (Ed.), ISKO: Encyclopedia of Knowledge Organization. International Society for Knowledge Organization
Open this publication in new window or tab >>Automatic subject indexing of text
2017 (English)In: ISKO: Encyclopedia of Knowledge Organization / [ed] Birger Hjørland, Claudio Gnoli, International Society for Knowledge Organization , 2017Chapter in book (Refereed)
Abstract [en]

Automatic subject indexing addresses problems of scale and sustainability and can be at the same time used to enrich existing metadata records, establish more connections across and between resources from various metadata and resource collections, and enhance consistency of the metadata. In this entry automatic subject indexing focuses on assigning index terms or classes from established knowledge organization systems (KOS) for subject indexing like thesauri, subject headings systems and classification systems. The following major approaches are discussed, in terms of their similarities and differences, advantages and disadvantages for automatic assigned indexing from KOSs: “text categorization”, “document clustering”, and “document classification”. Text categorization is perhaps the most widespread, machine-learning approach with what seems generally good reported performance. This, however, is dependent on availability of training corpora with documents already categorized which are in many cases not there. Document clustering automatically both creates groups of related documents and extracts names of subjects depicting the group at hand. It does not require training documents, but the reported automatically extracted terms and structures are not always of good quality, reflecting the underlying problems of the natural language; also, they both change when new documents are added to the collection and this mutability may not be user-friendly. Document classification re-uses the intellectual effort invested into creating KOSs for subject indexing and even simple string-matching algorithms have been reported to achieve good results because one concept can be described using a number of different terms, including equivalent, related, narrower and broader terms. Finally, applicability of automatic subject indexing to operative information systems and challenges of evaluation are outlined, suggesting the need for more research.

Place, publisher, year, edition, pages
International Society for Knowledge Organization, 2017
National Category
Information Studies
Research subject
Humanities, Library and Information Science
Identifiers
urn:nbn:se:lnu:diva-68349 (URN)
Available from: 2017-10-13 Created: 2017-10-13 Last updated: 2017-10-30Bibliographically approved
Golub, K. & Hansson, J. (2017). (Big) Data in Library and Information Science: A Brief Overview of Some Important Problem Areas. Journal of universal computer science (Online), 23(11), 1098-1108
Open this publication in new window or tab >>(Big) Data in Library and Information Science: A Brief Overview of Some Important Problem Areas
2017 (English)In: Journal of universal computer science (Online), ISSN 0948-695X, E-ISSN 0948-6968, Vol. 23, no 11, p. 1098-1108Article in journal (Refereed) Published
Abstract [en]

Libraries hold a long history of a multidimensional focus on collecting, storing, organizing, preserving and providing access to information resources for various types of users. Data is nothing new to Library and Information Science (LIS) and Big Data presents a quantitative expansion of an already well-known object of study. Scholarly communication, data sharing and data curation are three areas related to data in LIS and are discussed in this paper in the light of current developments as well as from the perspective of attaining the research area relevance in the discipline over time. Big Data, new technologies and networked research environments will continue to increase both in numbers and size. LIS is rapidly developing tools to meet the opportunities arising - through educational initiatives and the development of new research areas such as data curation and altmetrics. Since social and political demands for open data grow, these issues are pressing.

Keywords
bibliometrics, big data, data curation, data sharing, library and information science, scholarly communication
National Category
Information Studies
Research subject
Humanities, Library and Information Science
Identifiers
urn:nbn:se:lnu:diva-72040 (URN)000429070900007 ()
Available from: 2018-03-30 Created: 2018-03-30 Last updated: 2018-06-28Bibliographically approved
Golub, K., Hansson, J. & Seldén, L. (2017). Cult of the "I": Organizational symbolism and curricula in three Scandinavian iSchools with comparisons to three American. Journal of Documentation, 73(1), 48-74
Open this publication in new window or tab >>Cult of the "I": Organizational symbolism and curricula in three Scandinavian iSchools with comparisons to three American
2017 (English)In: Journal of Documentation, ISSN 0022-0418, E-ISSN 1758-7379, Vol. 73, no 1, p. 48-74Article in journal (Refereed) Published
Abstract [en]

Purpose

The purpose of the paper is to analyse three Scandinavian iSchools in Denmark, Norway and Sweden with regard to their intentions of becoming iSchools and curriculum content in relation to these intentions. By doing so, a picture will be given of the international expansion of the iSchool concept in terms of organisational symbolism and practical educational content. In order to underline the approaches of the Scandinavian schools, comparisons are made to three American iSchools.

Design/methodology/approach

The study is framed through theory on organisational symbolism and the intentions of the iSchool movement as formulated in its vision statements. Empirically, the study consists of two parts: close readings of three documents outlining the considerations of three Scandinavian LIS schools before applying for the iSchool status, and statistical analysis of 427 syllabi from master level courses at three Scandinavian and three American iSchools.

Findings

All three Scandinavian schools, analysed, have recently become iSchools, and though some differences are visible, it is hard to distinguish anything in their syllabi as carriers of what can be described as an iSchool identity. In considering iSchool identity, it instead benefits on a symbolic level that are most prominent, such as branding, social visibility and the possible attraction of new student groups. The traditionally strong relation to national library sectors are emphasised as important to maintain, specifically in Norway and Sweden.

Research limitations/implications

The study is done on iSchools in Denmark, Norway and Sweden with empirical comparison to three American schools. These comparisons face the challenge of meeting the educational system and programme structure of each individual country. Despite this, findings prove possible to use as ground for conclusions, although empirical generalisations concerning, for instance, other countries must be made with caution.

Practical implications

This study highlights the practical challenges met in international expansion of the iSchool movement, both on a practical and symbolic level. Both the iSchool Caucus and individual schools considering becoming iSchools may use these findings as a point of reference in development and decision making.

Originality/value

This is an original piece of research from which the results may contribute to the international development of the iSchool movement, and extend the theoretical understanding of the iSchool movement as an educational and organisational construct.

Place, publisher, year, edition, pages
Emerald Group Publishing Limited, 2017
Keywords
Denmark, Norway, Sweden, iSchools, Library and Information Science education, Organizational symbolism
National Category
Information Studies
Research subject
Humanities, Library and Information Science
Identifiers
urn:nbn:se:lnu:diva-59563 (URN)10.1108/JD-04-2016-0042 (DOI)000395677700004 ()
Available from: 2017-01-02 Created: 2017-01-02 Last updated: 2018-05-17Bibliographically approved
Golub, K., Milrad, M., Ping Huang, M., Mikko, T., Matres, I. & Bergsland, A. (2017). Current efforts, perspectives and challenges related to Digital Humanities in Nordic countries. In: Koraljka Golub, Marcelo Milrad (Ed.), DH 2016. Digital Humanities 2016: Extended Papers of the International Symposium on Digital Humanities (DH 2016). Växjö, Sweden, November, 7-8, 2016. Paper presented at International Symposium on Digital Humanities (DH 2016), Växjö, Sweden, November, 7-8, 2016 (pp. 119-125). CEUR-WS.org
Open this publication in new window or tab >>Current efforts, perspectives and challenges related to Digital Humanities in Nordic countries
Show others...
2017 (English)In: DH 2016. Digital Humanities 2016: Extended Papers of the International Symposium on Digital Humanities (DH 2016). Växjö, Sweden, November, 7-8, 2016 / [ed] Koraljka Golub, Marcelo Milrad, CEUR-WS.org , 2017, p. 119-125Conference paper, Published paper (Refereed)
Abstract [en]

This paper reports on a panel discussion at the International Digital Humanities (DH) Symposium, held in Växjö, 7-8 November 2016. The panel was organized to carry out a review of different DH initiatives related to current projects, educational initiatives and research and development activities, principally from the following universities: Linnaeus University, Sweden; Aarhus University, Denmark; University of Helsinki, Finland; and the Norwegian University for Science and Technology, Norway. Furthermore, the report proposes the formation of a Nordic hub of DARIAH-EU (Digital Research Infrastructure for the Arts and Humanities) and the challenges and opportunities arising from it. Opportunities include, for example: joint research and innovation efforts, education, expertise and experience exchange, and bringing in international perspectives to address transnational and regional challenges. The following challenges have been identified, namely: student recruitment, job opportunities in an emerging new market for graduates, and funding schemes.

Place, publisher, year, edition, pages
CEUR-WS.org, 2017
Series
CEUR Workshop Proceedings, ISSN 1613-0073 ; 2021
Keywords
Digital Humanities, Nordic Hub, DARIAH EU
National Category
Other Humanities not elsewhere specified Information Systems, Social aspects
Research subject
Humanities
Identifiers
urn:nbn:se:lnu:diva-69846 (URN)
Conference
International Symposium on Digital Humanities (DH 2016), Växjö, Sweden, November, 7-8, 2016
Available from: 2018-01-15 Created: 2018-01-15 Last updated: 2018-01-19Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0003-4169-4777

Search in DiVA

Show all publications