The twenty-first century of structural engineering research: A topic modeling approach

Aiming at disclosing a general research landscape of structural engineering in the twenty-first century, this study applies the latent Dirichlet allocation (LDA), a topic modeling approach, to analyze 51,346 article abstracts from 23 prestigious journals in structural engineering with a publication period from 2000 to 2020. The LDA analyzes the literature inventory by extracting 50 distinguishable wordclouds, each centered around one distinct research theme and assigned a unique topic name. Subsequently, various measures have been proposed to integrate the posterior distributions of these research topics with article information such as publication year, journal name, and correspondence address. The increase index identifies five cold and hot topics, which reflect the shift of research interests in the community. Emerging research topics such as seismic risk assessment and composite material have received much more attention in recent years. Moreover, advanced metrics have been proposed to analyze the research similarity and evolution across different journals and countries/regions. As discussed in the paper, analysis findings would enable community stakeholders (e.g., students, engineers, researchers, conference organizers, journal editors, funding agencies) to explore the state of the research and develop viable strategies to further foster the healthy growth of the community. Such strategies can be (1) researchers submitting a paper to the most appropriate journal; (2) journal editors adjusting the journal focus to enhance its impact; and (3) funding agencies prioritizing research supports that best fit regional needs and circumstances, among others.