Uncovering the Organizational Vulnerability toward Construction Project Accidents: BERTopic-Based Text Mining Analysis

Construction projects are renowned for their high-risk work environments, complex process flow, and stringent time and cost constraints, which impose prolonged pressure on project organizations, particularly for vulnerable organizations, where any minor perturbation may also disrupt normal operations, potentially leading to severe safety accidents. Hence, exploring how to mitigate project organizations’ vulnerability effectively is critical to enhancing project safety performance. However, the current understanding of organizational vulnerability in construction projects is limited. There is a lack of systematic insights into the structure, distribution, and differentiated vulnerability characteristics within project organizations, as well as practical evidence to identify and mitigate vulnerability hazards. To this end, this study adopts a big data perspective and employs BERTopic to uncover organizational vulnerability characteristics from construction project accident investigation reports. Expert knowledge from focus group discussions is also incorporated to systematically identify 20 organizational vulnerability topics. Building on this, common features among the topics are qualitatively analyzed to construct an integrated framework of organizational vulnerability toward construction project accidents, encompassing exposure, rigidity, and susceptibility. Based on the constructed framework, document embedding and dimensionality reduction techniques are employed to quantitatively analyze the distribution of organizational vulnerability and clarify key directions for vulnerability management. Finally, a comparative analysis of the vulnerability distribution and intensity is conducted for project stakeholders through topic modeling that captures the differentiated characteristics of each stakeholder. Based on these findings, a practical checklist was developed to assist project management teams in identifying organizational vulnerabilities related to construction project accidents during actual operations. The results show that organizational exposure is the most prevalent vulnerability feature, followed by susceptibility and rigidity. Moreover, significant variations in vulnerability are observed among project stakeholders. The research findings enrich the existing knowledge base by providing a structured framework for understanding organizational vulnerability. Practical guidance is offered to help construction project organizations address the vulnerabilities of various project stakeholders.

Authors

Institutions

Publication Details

Journal
Journal of Construction Engineering and Management
Published
2025-08-29
DOI
https://doi.org/10.1061/jcemd4.coeng-15499
Citations
2
Primary Topic
Occupational Health and Safety Research
Type
article
Field-Weighted Citation Impact
3.08
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Uncovering the Organizational Vulnerability toward Construction Project Accidents: BERTopic-Based Text Mining Analysis

Guangyan Sun, Lingyun Mi, Yuguo Zhang, Wenshun Wang et al.
2 citations
Journal of Construction Engineering and Management
Occupational Health and Safety Research
3.08
article

Uncovering the Organizational Vulnerability toward Construction Project Accidents: BERTopic-Based Text Mining Analysis

Guangyan Sun, Lingyun Mi, Yuguo Zhang, Wenshun Wang, Li Wang, Lijie Qiao, Min Tao
article en
2 citations

Abstract

Construction projects are renowned for their high-risk work environments, complex process flow, and stringent time and cost constraints, which impose prolonged pressure on project organizations, particularly for vulnerable organizations, where any minor perturbation may also disrupt normal operations, potentially leading to severe safety accidents. Hence, exploring how to mitigate project organizations’ vulnerability effectively is critical to enhancing project safety performance. However, the current understanding of organizational vulnerability in construction projects is limited. There is a lack of systematic insights into the structure, distribution, and differentiated vulnerability characteristics within project organizations, as well as practical evidence to identify and mitigate vulnerability hazards. To this end, this study adopts a big data perspective and employs BERTopic to uncover organizational vulnerability characteristics from construction project accident investigation reports. Expert knowledge from focus group discussions is also incorporated to systematically identify 20 organizational vulnerability topics. Building on this, common features among the topics are qualitatively analyzed to construct an integrated framework of organizational vulnerability toward construction project accidents, encompassing exposure, rigidity, and susceptibility. Based on the constructed framework, document embedding and dimensionality reduction techniques are employed to quantitatively analyze the distribution of organizational vulnerability and clarify key directions for vulnerability management. Finally, a comparative analysis of the vulnerability distribution and intensity is conducted for project stakeholders through topic modeling that captures the differentiated characteristics of each stakeholder. Based on these findings, a practical checklist was developed to assist project management teams in identifying organizational vulnerabilities related to construction project accidents during actual operations. The results show that organizational exposure is the most prevalent vulnerability feature, followed by susceptibility and rigidity. Moreover, significant variations in vulnerability are observed among project stakeholders. The research findings enrich the existing knowledge base by providing a structured framework for understanding organizational vulnerability. Practical guidance is offered to help construction project organizations address the vulnerabilities of various project stakeholders.

Journal of Construction Engineering and ManagementVol. 151(11)
China University of Mining and Technology (CN)
Openalex Percentile: Top 8%
Occupational Health and Safety Research
3.08
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.