Metaresearching Structural Engineering Using Text Mining: Trend Identifications and Knowledge Gap Discoveries
Bibliographic 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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.016 | 0.054 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.046 | 0.035 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.006 | 0.008 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".