• Login
    View Item 
    •   DSpace Home
    • ASCE
    • Journal of Structural Engineering
    • View Item
    •   DSpace Home
    • ASCE
    • Journal of Structural Engineering
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Metaresearching Structural Engineering Using Text Mining: Trend Identifications and Knowledge Gap Discoveries

    Thumbnail
    View/Open
    %28ASCE%29ST.1943-541X.0002523.pdf (8.701Mb)
    Date
    2020
    Author
    Mohamed Ezzeldin
    Wael El-Dakhakhni
    Metadata
    Show full item record
    Abstract
    The significant increase in the number of journal paper submissions/publications in the last decades has been paralleled by a shift to (mainly) on-line publication and digital archiving of past research articles. This situation has created an opportunity to metaresearch (conduct research on research) structural engineering through benefiting from emerging computational techniques such as data mining to track historical and current research focuses and trends and to better identify evolving research themes and discover possible cross-cutting knowledge gaps. Such metaresearch can benefit all structural engineering community stakeholders (e.g., researchers, designers, and funding agencies) in multiple ways including research resource realignments and optimizations to meet current and future research needs. The current study utilizes text mining—a class of data mining—to analyze published structural engineering research over 26 years. The considered dataset represents more than 11,000 articles, published in the two leading structural engineering journals (Journal of Structural Engineering and Engineering Structures) from 1991 to 2016. Following the collection and preparation of the training and testing datasets, the latent Dirichlet allocation (LDA) topic modeling technique is utilized to identify, classify, and categorize articles in terms of their topics, characterized by relevant technical terms. Subsequently, quantitative analyses are used to evaluate the temporal inclusion trends within the 11,000 article dataset. The LDA technique is also reapplied on only articles published between 2012 and 2016, to identify recent research topic developments and investigate the correlation between these topics and their counterparts covering the entire 26-year study period. Finally a word co-occurrence network and a topic interlinkage matrix are also developed, providing visual tools to rapidly evaluate structural engineering research subfield co-occurrences and linkage strengths. The overarching aim of this metaresearch is to identify understudied intersections of structural engineering subfields and highlight Blue Ocean opportunities at the interfaces of structural engineering and other established fields and emerging technologies.
    URI
    http://yetl.yabesh.ir/yetl1/handle/yetl/4266554
    Collections
    • Journal of Structural Engineering

    DSpace software copyright © 2002-2015  DuraSpace
    Contact Us | Send Feedback
    Theme by 
    @mire NV
     

     

    Browse

    All of DSpaceCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

    My Account

    LoginRegister

    Statistics

    View Usage Statistics

    DSpace software copyright © 2002-2015  DuraSpace
    Contact Us | Send Feedback
    Theme by 
    @mire NV