IDEAS home Printed from https://ideas.repec.org/a/spr/scient/v128y2023i5d10.1007_s11192-023-04689-3.html
   My bibliography  Save this article

Research proposal content extraction using natural language processing and semi-supervised clustering: A demonstration and comparative analysis

Author

Listed:
  • Benjamin M. Knisely

    (United States Army Medical Research and Development Command)

  • Holly H. Pavliscsak

    (United States Army Medical Research and Development Command)

Abstract

Funding institutions often solicit text-based research proposals to evaluate potential recipients. Leveraging the information contained in these documents could help institutions understand the supply of research within their domain. In this work, an end-to-end methodology for semi-supervised document clustering is introduced to partially automate classification of research proposals based on thematic areas of interest. The methodology consists of three stages: (1) manual annotation of a document sample; (2) semi-supervised clustering of documents; (3) evaluation of cluster results using quantitative metrics and qualitative ratings (coherence, relevance, distinctiveness) by experts. The methodology is described in detail to encourage replication and is demonstrated on a real-world data set. This demonstration sought to categorize proposals submitted to the US Army Telemedicine and Advanced Technology Research Center (TATRC) related to technological innovations in military medicine. A comparative analysis of method features was performed, including unsupervised vs. semi-supervised clustering, several document vectorization techniques, and several cluster result selection strategies. Outcomes suggest that pretrained Bidirectional Encoder Representations from Transformers (BERT) embeddings were better suited for the task than older text embedding techniques. When comparing expert ratings between algorithms, semi-supervised clustering produced coherence ratings ~ 25% better on average compared to standard unsupervised clustering with negligible differences in cluster distinctiveness. Last, it was shown that a cluster result selection strategy that balances internal and external validity produced ideal results. With further refinement, this methodological framework shows promise as a useful analytical tool for institutions to unlock hidden insights from untapped archives and similar administrative document repositories.

Suggested Citation

  • Benjamin M. Knisely & Holly H. Pavliscsak, 2023. "Research proposal content extraction using natural language processing and semi-supervised clustering: A demonstration and comparative analysis," Scientometrics, Springer;Akadémiai Kiadó, vol. 128(5), pages 3197-3224, May.
    • Handle: RePEc:spr:scient:v:128:y:2023:i:5:d:10.1007_s11192-023-04689-3
    DOI: 10.1007/s11192-023-04689-3
    as

    Download full text from publisher

    File URL: http://link.springer.com/10.1007/s11192-023-04689-3
    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/s11192-023-04689-3?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. Jakob Edler & Wouter P Boon, 2018. "‘The next generation of innovation policy: Directionality and the role of demand-oriented instruments’—Introduction to the special section," Science and Public Policy, Oxford University Press, vol. 45(4), pages 433-434.
    2. Leah G. Nichols, 2014. "A topic model approach to measuring interdisciplinarity at the National Science Foundation," Scientometrics, Springer;Akadémiai Kiadó, vol. 100(3), pages 741-754, September.
    3. Zhang, Yi & Lu, Jie & Liu, Feng & Liu, Qian & Porter, Alan & Chen, Hongshu & Zhang, Guangquan, 2018. "Does deep learning help topic extraction? A kernel k-means clustering method with word embedding," Journal of Informetrics, Elsevier, vol. 12(4), pages 1099-1117.
    4. Brock, Guy & Pihur, Vasyl & Datta, Susmita & Datta, Somnath, 2008. "clValid: An R Package for Cluster Validation," Journal of Statistical Software, Foundation for Open Access Statistics, vol. 25(i04).
    5. Jaeyoung Kim & Janghyeok Yoon & Eunjeong Park & Sungchul Choi, 2020. "Patent document clustering with deep embeddings," Scientometrics, Springer;Akadémiai Kiadó, vol. 123(2), pages 563-577, May.
    6. Yuan Zhou & Heng Lin & Yufei Liu & Wei Ding, 2019. "A novel method to identify emerging technologies using a semi-supervised topic clustering model: a case of 3D printing industry," Scientometrics, Springer;Akadémiai Kiadó, vol. 120(1), pages 167-185, July.
    7. Kevin W. Boyack & Caleb Smith & Richard Klavans, 2018. "Toward predicting research proposal success," Scientometrics, Springer;Akadémiai Kiadó, vol. 114(2), pages 449-461, February.
    8. Ebadi, Ashkan & Tremblay, Stéphane & Goutte, Cyril & Schiffauerova, Andrea, 2020. "Application of machine learning techniques to assess the trends and alignment of the funded research output," Journal of Informetrics, Elsevier, vol. 14(2).
    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. Lu Huang & Yijie Cai & Erdong Zhao & Shengting Zhang & Yue Shu & Jiao Fan, 2022. "Measuring the interdisciplinarity of Information and Library Science interactions using citation analysis and semantic analysis," Scientometrics, Springer;Akadémiai Kiadó, vol. 127(11), pages 6733-6761, November.
    2. Yuan Zhou & Fang Dong & Yufei Liu & Liang Ran, 2021. "A deep learning framework to early identify emerging technologies in large-scale outlier patents: an empirical study of CNC machine tool," Scientometrics, Springer;Akadémiai Kiadó, vol. 126(2), pages 969-994, February.
    3. Yuan Zhou & Fang Dong & Yufei Liu & Zhaofu Li & JunFei Du & Li Zhang, 2020. "Forecasting emerging technologies using data augmentation and deep learning," Scientometrics, Springer;Akadémiai Kiadó, vol. 123(1), pages 1-29, April.
    4. Patrick Zschech & Kai Heinrich & Raphael Bink & Janis S. Neufeld, 2019. "Prognostic Model Development with Missing Labels," Business & Information Systems Engineering: The International Journal of WIRTSCHAFTSINFORMATIK, Springer;Gesellschaft für Informatik e.V. (GI), vol. 61(3), pages 327-343, June.
    5. Dejing Kong & Jianzhong Yang & Lingfeng Li, 2020. "Early identification of technological convergence in numerical control machine tool: a deep learning approach," Scientometrics, Springer;Akadémiai Kiadó, vol. 125(3), pages 1983-2009, December.
    6. Choi, Jaewoong & Yoon, Janghyeok, 2022. "Measuring knowledge exploration distance at the patent level: Application of network embedding and citation analysis," Journal of Informetrics, Elsevier, vol. 16(2).
    7. Rik B Braams & Joeri H Wesseling & Albert J Meijer & Marko P Hekkert, 2022. "Understanding why civil servants are reluctant to carry out transition tasks [“Legitimation” and “development of positive Externalities”: Two Key Processes in the Formation Phase of Technological I," Science and Public Policy, Oxford University Press, vol. 49(6), pages 905-914.
    8. Zuo, Zhiya & Zhao, Kang, 2018. "The more multidisciplinary the better? – The prevalence and interdisciplinarity of research collaborations in multidisciplinary institutions," Journal of Informetrics, Elsevier, vol. 12(3), pages 736-756.
    9. Patrick S. Roberts & Jon Schmid, 2022. "Government‐led innovation acceleration: Case studies of US federal government innovation and technology acceleration organizations," Review of Policy Research, Policy Studies Organization, vol. 39(3), pages 353-378, May.
    10. Gainbi Park & Zengwang Xu, 2022. "The constituent components and local indicator variables of social vulnerability index," Natural Hazards: Journal of the International Society for the Prevention and Mitigation of Natural Hazards, Springer;International Society for the Prevention and Mitigation of Natural Hazards, vol. 110(1), pages 95-120, January.
    11. Fernandez Martinez, Roberto & Lostado Lorza, Ruben & Santos Delgado, Ana Alexandra & Piedra, Nelson, 2021. "Use of classification trees and rule-based models to optimize the funding assignment to research projects: A case study of UTPL," Journal of Informetrics, Elsevier, vol. 15(1).
    12. repec:oup:rseval:v:32:y:2024:i:2:p:213-227. is not listed on IDEAS
    13. Ran Xu & Navid Ghaffarzadegan, 2018. "Neuroscience bridging scientific disciplines in health: Who builds the bridge, who pays for it?," Scientometrics, Springer;Akadémiai Kiadó, vol. 117(2), pages 1183-1204, November.
    14. Paul Donner, 2021. "Validation of the Astro dataset clustering solutions with external data," Scientometrics, Springer;Akadémiai Kiadó, vol. 126(2), pages 1619-1645, February.
    15. Lu Huang & Xiang Chen & Yi Zhang & Changtian Wang & Xiaoli Cao & Jiarun Liu, 2022. "Identification of topic evolution: network analytics with piecewise linear representation and word embedding," Scientometrics, Springer;Akadémiai Kiadó, vol. 127(9), pages 5353-5383, September.
    16. Hansmeier Hendrik & Kroll Henning, 2024. "The geography of eco-innovations and sustainability transitions: A systematic comparison," ZFW – Advances in Economic Geography, De Gruyter, vol. 68(2), pages 125-143.
    17. Jihong Chen & Kai Zhang & Yuan Zhou & Yufei Liu & Lingfeng Li & Zheng Chen & Li Yin, 2019. "Exploring the Development of Research, Technology and Business of Machine Tool Domain in New-Generation Information Technology Environment Based on Machine Learning," Sustainability, MDPI, vol. 11(12), pages 1-38, June.
    18. Borke, Lukas & Härdle, Wolfgang Karl, 2016. "Q3-D3-Lsa," SFB 649 Discussion Papers 2016-049, Humboldt University Berlin, Collaborative Research Center 649: Economic Risk.
    19. Ana Alina Tudoran, 2022. "A machine learning approach to identifying decision-making styles for managing customer relationships," Electronic Markets, Springer;IIM University of St. Gallen, vol. 32(1), pages 351-374, March.
    20. Wu, Han-Ming, 2011. "On biological validity indices for soft clustering algorithms for gene expression data," Computational Statistics & Data Analysis, Elsevier, vol. 55(5), pages 1969-1979, May.
    21. Xiaowen Xi & Jiaqi Wei & Ying Guo & Weiyu Duan, 2022. "Academic collaborations: a recommender framework spanning research interests and network topology," Scientometrics, Springer;Akadémiai Kiadó, vol. 127(11), pages 6787-6808, November.

    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:128:y:2023:i:5:d:10.1007_s11192-023-04689-3. 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.