Early detection and mitigation of social conflict in civil infrastructure projects is essential due to its significant impact on project performance and social governance. Nevertheless, there is no scientific system for monitoring conflict drivers in a timely manner in practice. Furthermore, previous studies of social conflict in the civil engineering and management domains have relied on manual literature reviews and case studies. Although these qualitative approaches have provided context-specific insights, they are limited in their generalizability and broad perspectives. Against this backdrop, this study presents an automated process for detecting conflict drivers from news articles using ChatGPT. The authors collected news articles related to civil infrastructure projects implemented in the Republic of Korea using web crawling. Then, ChatGPT was used to extract conflict-related keyphrases from the article collections and classify the keyphrases into predefined conflict drivers. The result showed a notable performance with a micro average F1-score of 85.7%. Moreover, the authors confirmed the validity of the keyphrase extraction and classification results through two illustrative case studies. The proposed process and methods contribute to facilitating data-driven conflict management. Although this study focused on conflict drivers of public infrastructure projects, other types of information extraction tasks can benefit from the presented framework.

“High risk high return” is a general rule in the overall industry; however, high-risk projects in the construction industry frequently fail to yield a high return. In order to achieve a sustainable business in the international construction market, contractors require an average to high return yield under high-risk conditions. This study aims to reveal what risk factors and risk management performance enables high-risk projects to yield high returns. The study investigated 124 international construction projects by Korean contractors and classified them into four groups: high-risk high-return (HH), high-risk low-return (HL), low-risk high-return (LH), and low-risk low-return (LL). The study found that risk assessment accuracy was the most important trigger in discriminating between high return projects (HH, LH) and low return projects (HL, LL), whereas risk mitigation performance showed little difference between high return and low return projects. In addition, the contingency amount did not significantly affect project return in HL, LH, and LL projects, but HH projects showed a positive relation between contingency and predicted risk amount. This article contributes to recognizing the differences between high return and low return projects and provides insights for practitioners into the relation between risk management performance and high returns in different risk conditions.