IDEAS home Printed from https://ideas.repec.org/a/spr/scient/v129y2024i7d10.1007_s11192-024-05055-7.html
   My bibliography  Save this article

Using word embedding to detect keywords in texts modeled as complex networks

Author

Listed:
  • Jorge A. V. Tohalino

    (University of São Paulo)

  • Thiago C. Silva

    (Universidade Católica de Brasília)

  • Diego R. Amancio

    (University of São Paulo)

Abstract

Detecting keywords in texts is a task of paramount importance for many text mining applications. Graph-based techniques have been commonly used to automatically find the key concepts in texts. However, the integration of valuable information provided by embeddings to enrich the graph structure has not been widely used. In this context, this paper aims to address the following question: can the quality of extracted keywords from a co-occurrence network be enhanced by integrating embeddings to enrich the network structure? In the adopted model, texts are represented as co-occurrence networks, where nodes are words and edges are established either by contextual or semantical similarity. Two embedding approaches were used: Word2vec and Bidirectional Encoder Representations from Transformers (BERT). The results indicate that using virtual edges can effectively enhance the discriminative capacity of co-occurrence networks. The best performance was achieved by incorporating a limited proportion of virtual (embedding) edges. A comparison of the structural and dynamical network metrics demonstrated that the degree, PageRank, and accessibility metrics exhibited superior performance in the proposed model.

Suggested Citation

  • Jorge A. V. Tohalino & Thiago C. Silva & Diego R. Amancio, 2024. "Using word embedding to detect keywords in texts modeled as complex networks," Scientometrics, Springer;Akadémiai Kiadó, vol. 129(7), pages 3599-3623, July.
    • Handle: RePEc:spr:scient:v:129:y:2024:i:7:d:10.1007_s11192-024-05055-7
    DOI: 10.1007/s11192-024-05055-7
    as

    Download full text from publisher

    File URL: http://link.springer.com/10.1007/s11192-024-05055-7
    File Function: Abstract
    Download Restriction: Access to the full text of the articles in this series is restricted.
    File URL: https://libkey.io/10.1007/s11192-024-05055-7?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to search for a different version of it.

    References listed on IDEAS

    as
    1. Beakcheol Jang & Inhwan Kim & Jong Wook Kim, 2019. "Word2vec convolutional neural networks for classification of news articles and tweets," PLOS ONE, Public Library of Science, vol. 14(8), pages 1-20, August.
    2. Gert Sabidussi, 1966. "The centrality index of a graph," Psychometrika, Springer;The Psychometric Society, vol. 31(4), pages 581-603, December.
    3. Jeaneth Machicao & Edilson A Corrêa Jr. & Gisele H B Miranda & Diego R Amancio & Odemir M Bruno, 2018. "Authorship attribution based on Life-Like Network Automata," PLOS ONE, Public Library of Science, vol. 13(3), pages 1-21, March.
    4. Diego R. Amancio & Osvaldo N. Oliveira jr & Luciano F. Costa, 2015. "Topological-collaborative approach for disambiguating authors’ names in collaborative networks," Scientometrics, Springer;Akadémiai Kiadó, vol. 102(1), pages 465-485, January.
    5. Adilson Vital & Diego R. Amancio, 2022. "A comparative analysis of local similarity metrics and machine learning approaches: application to link prediction in author citation networks," Scientometrics, Springer;Akadémiai Kiadó, vol. 127(10), pages 6011-6028, October.
    6. J. P. Herrera & P. A. Pury, 2008. "Statistical keyword detection in literary corpora," The European Physical Journal B: Condensed Matter and Complex Systems, Springer;EDP Sciences, vol. 63(1), pages 135-146, May.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. De Masi, G. & Giovannetti, G. & Ricchiuti, G., 2013. "Network analysis to detect common strategies in Italian foreign direct investment," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 392(5), pages 1202-1214.
    2. Fogel, Kathy & Jandik, Tomas & McCumber, William R., 2018. "CFO social capital and private debt," Journal of Corporate Finance, Elsevier, vol. 52(C), pages 28-52.
    3. Jia Zhu & Xingcheng Wu & Xueqin Lin & Changqin Huang & Gabriel Pui Cheong Fung & Yong Tang, 2018. "A novel multiple layers name disambiguation framework for digital libraries using dynamic clustering," Scientometrics, Springer;Akadémiai Kiadó, vol. 114(3), pages 781-794, March.
    4. Hyuk-Soo Kwon & Jihong Lee & Sokbae Lee & Ryungha Oh, 2022. "Knowledge spillovers and patent citations: trends in geographic localization, 1976–2015," Economics of Innovation and New Technology, Taylor & Francis Journals, vol. 31(3), pages 123-147, April.
    5. Mengying Cui & David Levinson, 2018. "Accessibility analysis of risk severity," Transportation, Springer, vol. 45(4), pages 1029-1050, July.
    6. Fang, Ming & Francis, Bill & Hasan, Iftekhar & Wu, Qiang, 2022. "External social networks and earnings management," The British Accounting Review, Elsevier, vol. 54(2).
    7. Mario V. Tomasello & Mauro Napoletano & Antonios Garas & Frank Schweitzer, 2017. "The rise and fall of R&D networks," Industrial and Corporate Change, Oxford University Press and the Associazione ICC, vol. 26(4), pages 617-646.
    8. Tao, Qizhi & Li, Haoyu & Wu, Qun & Zhang, Ting & Zhu, Yingjun, 2019. "The dark side of board network centrality: Evidence from merger performance," Journal of Business Research, Elsevier, vol. 104(C), pages 215-232.
    9. repec:dau:papers:123456789/7616 is not listed on IDEAS
    10. Jackie Krafft & Francesco Quatraro, 2011. "The Dynamics of Technological Knowledge: From Linearity to Recombination," Chapters, in: Cristiano Antonelli (ed.), Handbook on the Economic Complexity of Technological Change, chapter 7, Edward Elgar Publishing.
    11. Zhao, Shuying & Sun, Shaowei, 2023. "Identification of node centrality based on Laplacian energy of networks," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 609(C).
    12. Wu, Tao & Xian, Xingping & Zhong, Linfeng & Xiong, Xi & Stanley, H. Eugene, 2018. "Power iteration ranking via hybrid diffusion for vital nodes identification," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 506(C), pages 802-815.
    13. Jamaati, Maryam & Mehri, Ali, 2018. "Text mining by Tsallis entropy," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 490(C), pages 1368-1376.
    14. Giulia Masi & Giorgio Ricchiuti, 2020. "From FDI network topology to macroeconomic instability," Journal of Economic Interaction and Coordination, Springer;Society for Economic Science with Heterogeneous Interacting Agents, vol. 15(1), pages 133-158, January.
    15. Wang, Feifei & Sun, Zejun & Gan, Quan & Fan, Aiwan & Shi, Hesheng & Hu, Haifeng, 2022. "Influential node identification by aggregating local structure information," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 593(C).
    16. Zamudio, César & Anokhin, Sergey & Kellermanns, Franz W., 2014. "Network analysis: A concise review and suggestions for family business research," Journal of Family Business Strategy, Elsevier, vol. 5(1), pages 63-71.
    17. Jing Yang & Yingwu Chen, 2011. "Fast Computing Betweenness Centrality with Virtual Nodes on Large Sparse Networks," PLOS ONE, Public Library of Science, vol. 6(7), pages 1-5, July.
    18. Li, Zhitao & Tang, Jinjun & Zhao, Chuyun & Gao, Fan, 2023. "Improved centrality measure based on the adapted PageRank algorithm for urban transportation multiplex networks," Chaos, Solitons & Fractals, Elsevier, vol. 167(C).
    19. Henderson, Geraldine R. & Iacobucci, Dawn & Calder, Bobby J., 1998. "Brand diagnostics: Mapping branding effects using consumer associative networks," European Journal of Operational Research, Elsevier, vol. 111(2), pages 306-327, December.
    20. Andrea Ancona & Roy Cerqueti & Gianluca Vagnani, 2023. "A novel methodology to disambiguate organization names: an application to EU Framework Programmes data," Scientometrics, Springer;Akadémiai Kiadó, vol. 128(8), pages 4447-4474, August.
    21. repec:hal:wpspec:info:hdl:2441/f6h8764enu2lskk9p5487a6cm is not listed on IDEAS
    22. Fan, Yaoyao & Jiang, Yuxiang & Jin, Pengcheng & Mai, Yong, 2023. "CEO network centrality and bank risk: Evidence from US Bank holding companies," Journal of Corporate Finance, Elsevier, vol. 83(C).

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:spr:scient:v:129:y:2024:i:7:d:10.1007_s11192-024-05055-7. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Sonal Shukla or Springer Nature Abstracting and Indexing (email available below). General contact details of provider: http://www.springer.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.