<abstract xmlns="http://www.w3.org/1999/xhtml"><sec id="j_jdis-2019-0010_s_005_w2aab3b7b5b1b6b1aab1c17b1Aa"><h3>Purpose</h3><p>To investigate the effectiveness of using node2vec on journal citation networks to represent journals as vectors for tasks such as clustering, science mapping, and journal diversity measure.</p></sec><sec id="j_jdis-2019-0010_s_006_w2aab3b7b5b1b6b1aab1c17b2Aa"><h3>Design/methodology/approach</h3><p>Node2vec is used in a journal citation network to generate journal vector representations.</p></sec><sec id="j_jdis-2019-0010_s_007_w2aab3b7b5b1b6b1aab1c17b3Aa"><h3>Findings</h3><p>1. Journals are clustered based on the node2vec trained vectors to form a science map. 2. The norm of the vector can be seen as an indicator of the diversity of journals. 3. Using node2vec trained journal vectors to determine the Rao-Stirling diversity measure leads to a better measure of diversity than that of direct citation vectors.</p></sec><sec id="j_jdis-2019-0010_s_008_w2aab3b7b5b1b6b1aab1c17b4Aa"><h3>Research limitations</h3><p>All analyses use citation data and only focus on the journal level.</p></sec><sec id="j_jdis-2019-0010_s_009_w2aab3b7b5b1b6b1aab1c17b5Aa"><h3>Practical implications</h3><p>Node2vec trained journal vectors embed rich information about journals, can be used to form a science map and may generate better values of journal diversity measures.</p></sec><sec id="j_jdis-2019-0010_s_010_w2aab3b7b5b1b6b1aab1c17b6Aa"><h3>Originality/value</h3><p>The effectiveness of node2vec in scientometric analysis is tested. Possible indicators for journal diversity measure are presented.</p></sec></abstract>

PurposeTo investigate the effectiveness of using node2vec on journal citation networks to represent journals as vectors for tasks such as clustering, science mapping, and journal diversity measure.Design/methodology/approachNode2vec is used in a journal citation network to generate journal vector representations.Findings1. Journals are clustered based on the node2vec trained vectors to form a science map. 2. The norm of the vector can be seen as an indicator of the diversity of journals. 3. Using node2vec trained journal vectors to determine the Rao-Stirling diversity measure leads to a better measure of diversity than that of direct citation vectors.Research limitationsAll analyses use citation data and only focus on the journal level.Practical implicationsNode2vec trained journal vectors embed rich information about journals, can be used to form a science map and may generate better values of journal diversity measures.Originality/valueThe effectiveness of node2vec in scientometric analysis is tested. Possible indicators for journal diversity measure are presented.

Node2vec Representation for Clustering Journals and as A Possible Measure of Diversity

Journal of Data and Information Science

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

PurposeTo investigate the effectiveness of using node2vec on journal citation networks to represent journals as vectors for tasks such as clustering, science...

Node2vec Representation for Clustering Journals and as A Possible Measure of Diversity

Article Category: Research Paper

Online veröffentlicht: 07. Juni 2019

Seitenbereich: 79 - 92

Eingereicht: 03. Apr. 2019

Akzeptiert: 09. Mai 2019

DOI: https://doi.org/10.2478/jdis-2019-0010

Schlüsselwörter
Science mapping, Diversity, Graph embedding, Vector norm

© 2019 Zhesi Shen, Fuyou Chen, Liying Yang, Jinshan Wu, published by Sciendo

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

Node2vec Representation for Clustering Journals and as A Possible Measure of Diversity

Article Category: Research Paper

Online veröffentlicht: 07. Juni 2019

Seitenbereich: 79 - 92

Eingereicht: 03. Apr. 2019

Akzeptiert: 09. Mai 2019

DOI: https://doi.org/10.2478/jdis-2019-0010

SchlüsselwörterScience mapping, Diversity, Graph embedding, Vector norm

© 2019 Zhesi Shen, Fuyou Chen, Liying Yang, Jinshan Wu, published by Sciendo

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

Schlüsselwörter
Science mapping, Diversity, Graph embedding, Vector norm