Erfani, A; Cui, Q and Cavanaugh, I (2021) An empirical analysis of risk similarity among major transportation projects using natural language processing. Journal of Construction Engineering and Management, 147(12): 04021175, ISSN 0733-9364
Abstract
Risk management is widely recognized as a best practice for public agencies to ensure the successful implementation of major transportation projects. The conventional approach to identify and evaluate project risks is dominated by getting input from subject matter experts at risk workshops. However, the uniqueness of such a risk assessment approach remains unexamined. How different are the risks among various projects? Does the risk register reflect the unique feature of a project? The goal of this study is to measure the similarity of project risks across various groups by evaluating 70 major transportation projects delivered under various methods. The similarity index is calculated at three levels, that is, the entire document of the risk register, individual risk item, and the probability and consequence of each risk using a systematic comparative analysis based on natural language processing (NLP) and a state-of-the-art deep learning algorithm named Word2vec. Our study reports a high similarity of risk registers among different projects at all three levels. The analysis does show a lower similarity of risk registers for public-private partnerships (P3) projects. The primary contributions of this study are (1) develop a new approach to analyze the risk registers at the project level as the main output of risk management practice, and (2) establish the relation of risk uniqueness and project delivery method in transportation projects. Results suggest that a data-driven approach may be possible to help project teams develop a common risk register while allowing the teams to focus on each project's unique risks.
| Item Type: | Article |
|---|---|
| Uncontrolled Keywords: | data analytics; natural language processing; project delivery method; risk management; risk register; transportation project |
| Index terms: | workshop, deep learning, partnership, risk management, best practice, risk assessment, project delivery, project team, implementation, comparative analysis, transportation project, risk register, state of the art, agency |
| Subjects: | project delivery, artificial intelligence, data analysis and analytics, contractual arrangements, business, research dissemination and communication, construction type, risk assessment, sociology, partnership management, infrastructure and transport systems, financial risk |
| Topics: | Digital Applications, Procurement, Construction Technology, Stakeholder Management, Risk Management, Engineering Principles, Project Management, Research Practice, Business Strategy, Cost Management |
| Descriptive scope: | 4 PCTA |
N.B. Descriptive scope is a count of how many of the five facets of empirical research are indicated by the words used in title, abstract and keywords. It is not intended as a judgement on the research; merely a count of the kind of word we would expect to indicate Phenomenon, Concepts, Theoretical framing, Empirical techniques, Analytical techniques. If all five are present, then a code of “5 PCTEA” will indicate this. If you feel the coding for this record is questionable, we welcome discussion around the terms we matched or the way we categorized them. The facet you would expect may not be coded, or a facet may be coded inappropriately. This can also bear on a larger question, of which facets should be treated as defining in construction management research. Please get in touch, and we will look at it. More details here