Automatic Classification of Swedish Metadata Using Dewey Decimal Classification: A Comparison of Approaches

With more and more digital collections of various information resources 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...

Full description

Bibliographic Details
Main Authors: Golub Koraljka, Hagelbäck Johan, Ardö Anders
Format: Article
Language:English
Published: Sciendo 2020-04-01
Series:Journal of Data and Information Science
Subjects:
Online Access:https://doi.org/10.2478/jdis-2020-0003
_version_ 1818755310012071936
author Golub Koraljka
Hagelbäck Johan
Ardö Anders
author_facet Golub Koraljka
Hagelbäck Johan
Ardö Anders
author_sort Golub Koraljka
collection DOAJ
description With more and more digital collections of various information resources 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 six machine learning algorithms as well as a string-matching algorithm based on characteristics of DDC.
first_indexed 2024-12-18T05:37:06Z
format Article
id doaj.art-cd00d5900c8749519784d13d2de0fbe9
institution Directory Open Access Journal
issn 2543-683X
language English
last_indexed 2024-12-18T05:37:06Z
publishDate 2020-04-01
publisher Sciendo
record_format Article
series Journal of Data and Information Science
spelling doaj.art-cd00d5900c8749519784d13d2de0fbe92022-12-21T21:19:17ZengSciendoJournal of Data and Information Science2543-683X2020-04-0151183810.2478/jdis-2020-0003Automatic Classification of Swedish Metadata Using Dewey Decimal Classification: A Comparison of ApproachesGolub Koraljka0Hagelbäck Johan1Ardö Anders2Department of Cultural Sciences, Faculty of Arts and Humanities, Linnaeus University, Växjö, SwedenDepartment of Computer Science and Media Technology, Faculty of Technology, Linnaeus University, Kalmar, SwedenDepartment of Electrical and Information Technology, Lund University, Lund, SwedenWith more and more digital collections of various information resources 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 six machine learning algorithms as well as a string-matching algorithm based on characteristics of DDC.https://doi.org/10.2478/jdis-2020-0003librisdewey decimal classificationautomatic classificationmachine learningsupport vector machinemultinomial naïve bayessimple linear networkstandard neural network1d convolutional neural networkrecurrent neural networkword embeddingsstring matching
spellingShingle Golub Koraljka
Hagelbäck Johan
Ardö Anders
Automatic Classification of Swedish Metadata Using Dewey Decimal Classification: A Comparison of Approaches
Journal of Data and Information Science
libris
dewey decimal classification
automatic classification
machine learning
support vector machine
multinomial naïve bayes
simple linear network
standard neural network
1d convolutional neural network
recurrent neural network
word embeddings
string matching
title Automatic Classification of Swedish Metadata Using Dewey Decimal Classification: A Comparison of Approaches
title_full Automatic Classification of Swedish Metadata Using Dewey Decimal Classification: A Comparison of Approaches
title_fullStr Automatic Classification of Swedish Metadata Using Dewey Decimal Classification: A Comparison of Approaches
title_full_unstemmed Automatic Classification of Swedish Metadata Using Dewey Decimal Classification: A Comparison of Approaches
title_short Automatic Classification of Swedish Metadata Using Dewey Decimal Classification: A Comparison of Approaches
title_sort automatic classification of swedish metadata using dewey decimal classification a comparison of approaches
topic libris
dewey decimal classification
automatic classification
machine learning
support vector machine
multinomial naïve bayes
simple linear network
standard neural network
1d convolutional neural network
recurrent neural network
word embeddings
string matching
url https://doi.org/10.2478/jdis-2020-0003
work_keys_str_mv AT golubkoraljka automaticclassificationofswedishmetadatausingdeweydecimalclassificationacomparisonofapproaches
AT hagelbackjohan automaticclassificationofswedishmetadatausingdeweydecimalclassificationacomparisonofapproaches
AT ardoanders automaticclassificationofswedishmetadatausingdeweydecimalclassificationacomparisonofapproaches