Machine Learning in Safety and Health Research: A Scientometric Analysis
Bibliographic record
Abstract
Safety and health are intricately interwoven and have become indispensable to the thriving business world and anthropology. It is concerned with ensuring employees’ physical, emotional, and mental well-being. Based on the Scopus and Web of Science databases, the current study intends to analyse the global research output on machine learning in safety and health. This study utilized ScientoPy and VOSviewer to delve into the annual growth, patterns of research communication on source titles, international collaboration among countries, and authors’ keyword analysis. This study found that the Web of Science database tracks the evolution of publications throughout time. PLoS One has surpassed all other source titles in terms of publishing activity. Also, this study indicated that US researchers are constantly working on machine learning in safety and health research and have developed significant collaborations with China and Australia. Between 2020 and 2021, the University of Toronto published 86% of all papers, outpacing other institutions. The keywords “machine learning”, “artificial intelligence”, “electronic health records”, “deep learning”, and “mental health” were the most popular and trending keywords in 2020 and 2021, and “artificial intelligence” appeared in most publications among others. Future researchers should conduct scoping or systematic literature reviews to elucidate the relationships between these terms. This study may entice the curiosity of practitioners and researchers to advance new knowledge in this field by being devoted to cutting-edge research in the contemporary philosophy of science, cognitive, and cultural anthropology on machine learning in safety and health research. In conclusion, this scientometric analysis demonstrates that machine learning in safety and health is a study domain that requires further refinement in future research, as this technology has the potential to significantly improve workplace safety and health through targeted applications with clear benefits.
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 | 0.053 | 0.197 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.003 | 0.006 |
| Bibliometrics | 0.199 | 0.308 |
| Science and technology studies | 0.003 | 0.002 |
| Scholarly communication | 0.009 | 0.006 |
| Open science | 0.001 | 0.005 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.005 | 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".