<abstract xmlns="http://www.w3.org/1999/xhtml"><sec><h3>Purpose</h3><p>The goal of this study is to explore whether deep learning based embedded models can provide a better visualization solution for large citation networks.</p></sec><sec><h3>Design/methodology/approach</h3><p>Our team compared the visualization approach borrowed from the deep learning community with the well-known bibliometric network visualization for large scale data. 47,294 highly cited papers were visualized by using three network embedding models plus the t-SNE dimensionality reduction technique. Besides, three base maps were created with the same dataset for evaluation purposes. All base maps used the classic OpenOrd method with different edge cutting strategies and parameters.</p></sec><sec><h3>Findings</h3><p>The network embedded maps with t-SNE preserve a very similar global structure to the full edges classic force-directed map, while the maps vary in local structure. Among them, the Node2Vec model has the best overall visualization performance, the local structure has been significantly improved and the maps’ layout has very high stability.</p></sec><sec><h3>Research limitations</h3><p>The computational and time costs of training are very high for network embedded models to obtain high dimensional latent vector. Only one dimensionality reduction technique was tested.</p></sec><sec><h3>Practical implications</h3><p>This paper demonstrates that the network embedding models are able to accurately reconstruct the large bibliometric network in the vector space. In the future, apart from network visualization, many classical vector-based machine learning algorithms can be applied to network representations for solving bibliometric analysis tasks.</p></sec><sec><h3>Originality/value</h3><p>This paper provides the first systematic comparison of classical science mapping visualization with network embedding based visualization on a large scale dataset. We showed deep learning based network embedding model with t-SNE can provide a richer, more stable science map. We also designed a practical evaluation method to investigate and compare maps.</p></sec></abstract>

PurposeThe goal of this study is to explore whether deep learning based embedded models can provide a better visualization solution for large citation networks.Design/methodology/approachOur team compared the visualization approach borrowed from the deep learning community with the well-known bibliometric network visualization for large scale data. 47,294 highly cited papers were visualized by using three network embedding models plus the t-SNE dimensionality reduction technique. Besides, three base maps were created with the same dataset for evaluation purposes. All base maps used the classic OpenOrd method with different edge cutting strategies and parameters.FindingsThe network embedded maps with t-SNE preserve a very similar global structure to the full edges classic force-directed map, while the maps vary in local structure. Among them, the Node2Vec model has the best overall visualization performance, the local structure has been significantly improved and the maps’ layout has very high stability.Research limitationsThe computational and time costs of training are very high for network embedded models to obtain high dimensional latent vector. Only one dimensionality reduction technique was tested.Practical implicationsThis paper demonstrates that the network embedding models are able to accurately reconstruct the large bibliometric network in the vector space. In the future, apart from network visualization, many classical vector-based machine learning algorithms can be applied to network representations for solving bibliometric analysis tasks.Originality/valueThis paper provides the first systematic comparison of classical science mapping visualization with network embedding based visualization on a large scale dataset. We showed deep learning based network embedding model with t-SNE can provide a richer, more stable science map. We also designed a practical evaluation method to investigate and compare maps.

Using Network Embedding to Obtain a Richer and More Stable Network Layout for a Large Scale Bibliometric Network

Department of Library, Information and Archives Management

University of Chinese Academy of Sciences

Library, University of Electronic Science and Technology of China

Journal of Data and Information Science

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

PurposeThe goal of this study is to explore whether deep learning based embedded models can provide a better visualization solution for large citation...

Using Network Embedding to Obtain a Richer and More Stable Network Layout for a Large Scale Bibliometric Network

Article Category: Research Paper

Pubblicato online: 08 dic 2020

Pagine: 154 - 177

Ricevuto: 01 lug 2020

Accettato: 20 ott 2020

DOI: https://doi.org/10.2478/jdis-2021-0006

Parole chiave
Scientometrics, Visualization, Essential science indicators, Bibliometric networks, Network embedding, Science mapping

© 2021 Ting Chen et al., published by Sciendo

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

Using Network Embedding to Obtain a Richer and More Stable Network Layout for a Large Scale Bibliometric Network

Article Category: Research Paper

Pubblicato online: 08 dic 2020

Pagine: 154 - 177

Ricevuto: 01 lug 2020

Accettato: 20 ott 2020

DOI: https://doi.org/10.2478/jdis-2021-0006

Parole chiaveScientometrics, Visualization, Essential science indicators, Bibliometric networks, Network embedding, Science mapping

© 2021 Ting Chen et al., published by Sciendo

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

Parole chiave
Scientometrics, Visualization, Essential science indicators, Bibliometric networks, Network embedding, Science mapping