<abstract xmlns="http://www.w3.org/1999/xhtml"><sec id="j_jdis.201613_s_006_w2aab2b8b5b1b7b1aab1c15b1Aa"><h3>Purpose</h3><p>This paper is an investigation of the effectiveness of the method of clustering biomedical journals through mining the content similarity of journal articles.</p></sec><sec id="j_jdis.201613_s_007_w2aab2b8b5b1b7b1aab1c15b2Aa"><h3>Design/methodology/approach</h3><p>3,265 journals in PubMed are analyzed based on article content similarity and Web usage, respectively. Comparisons of the two analysis approaches and a citation-based approach are given.</p></sec><sec id="j_jdis.201613_s_008_w2aab2b8b5b1b7b1aab1c15b3Aa"><h3>Findings</h3><p>Our results suggest that article content similarity is useful for clustering biomedical journals, and the content-similarity-based journal clustering method is more robust and less subject to human factors compared with the usage-based approach and the citation-based approach.</p></sec><sec id="j_jdis.201613_s_009_w2aab2b8b5b1b7b1aab1c15b4Aa"><h3>Research limitations</h3><p>Our paper currently focuses on clustering journals in the biomedical domain because there are a large volume of freely available resources such as PubMed and MeSH in this field. Further investigation is needed to improve this approach to fit journals in other domains.</p></sec><sec id="j_jdis.201613_s_010_w2aab2b8b5b1b7b1aab1c15b5Aa"><h3>Practical implications</h3><p>Our results show that it is feasible to catalog biomedical journals by mining the article content similarity. This work is also significant in serving practical needs in research portfolio analysis.</p></sec><sec id="j_jdis.201613_s_011_w2aab2b8b5b1b7b1aab1c15b6Aa"><h3>Originality/value</h3><p>To the best of our knowledge, we are among the first to report on clustering journals in the biomedical field through mining the article content similarity. This method can be integrated with existing approaches to create a new paradigm for future studies of journal clustering.</p></sec></abstract>

PurposeThis paper is an investigation of the effectiveness of the method of clustering biomedical journals through mining the content similarity of journal articles.Design/methodology/approach3,265 journals in PubMed are analyzed based on article content similarity and Web usage, respectively. Comparisons of the two analysis approaches and a citation-based approach are given.FindingsOur results suggest that article content similarity is useful for clustering biomedical journals, and the content-similarity-based journal clustering method is more robust and less subject to human factors compared with the usage-based approach and the citation-based approach.Research limitationsOur paper currently focuses on clustering journals in the biomedical domain because there are a large volume of freely available resources such as PubMed and MeSH in this field. Further investigation is needed to improve this approach to fit journals in other domains.Practical implicationsOur results show that it is feasible to catalog biomedical journals by mining the article content similarity. This work is also significant in serving practical needs in research portfolio analysis.Originality/valueTo the best of our knowledge, we are among the first to report on clustering journals in the biomedical field through mining the article content similarity. This method can be integrated with existing approaches to create a new paradigm for future studies of journal clustering.

Mining Related Articles for Automatic Journal Cataloging

National Center for Biotechnology Information

Journal of Data and Information Science

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

{"article-title":"Mining Related Articles for Automatic Journal Cataloging"}

PurposeThis paper is an investigation of the effectiveness of the method of clustering biomedical journals through mining the content similarity of journal...

Mining Related Articles for Automatic Journal Cataloging

Article Category: Research Paper

Published Online: Sep 01, 2017

Page range: 45 - 59

Received: Dec 14, 2015

Accepted: Feb 26, 2016

DOI: https://doi.org/10.20309/jdis.201613

Keywords
PubMed, Journals, Cluster, Catalog, Text mining, Research evaluation

© 2016 Yuqing Mao, Zhiyong Lu

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

Mining Related Articles for Automatic Journal Cataloging

Article Category: Research Paper

Published Online: Sep 01, 2017

Page range: 45 - 59

Received: Dec 14, 2015

Accepted: Feb 26, 2016

DOI: https://doi.org/10.20309/jdis.201613

KeywordsPubMed, Journals, Cluster, Catalog, Text mining, Research evaluation

© 2016 Yuqing Mao, Zhiyong Lu

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

Keywords
PubMed, Journals, Cluster, Catalog, Text mining, Research evaluation