Mapping Two Decades of AI in Construction Research: A Scientometric Analysis from the Sustainability and Construction Phases Lenses

The construction industry plays a vital role in the urbanization process and global economy, and there is a growing interest in utilizing artificial intelligence (AI) technologies to improve sustainability, productivity, and efficiency. However, there is a lack of comprehensive analysis regarding the progression of AI in the construction context, particularly from the sustainability angle. This study aims to fill this gap by conducting a scientometric analysis of AI research in construction by focusing on historical clusters, emerging trends, research clusters, and the correlation between sustainability pillars and key project stages. A Scopus search, between January 2000 and July 2023, was conducted that used 25 construction industry-related keywords, resulting in a total of 9564 publications. After evaluating practical AI applications in construction, 3710 publications were selected for further analysis using VOSviewer for visual diagrams and to further understand connections and patterns between literature. The findings revealed that: (a) Literature on AI in construction has experienced steady growth over the past two decades; (b) Machine learning, deep learning, and big data are seen as the key enabling digital technologies in the construction sector’s performance; (c) Economic and governance pillars of sustainability exhibit the highest potential for AI adoption; (d) Design and construction phases demonstrate substantial advantages for AI adoption; (e) AI technologies have become, despite adoption challenges, a strong driver of construction industry modernization, and; (f) By incorporating AI, the construction industry can advance towards a more sustainable future by consolidating its processes and practices.

This creative work has been published under the Creative Commons Attribution 4.0 International (CC-BY 4.0) license which allows copying, and redistribution as well as adaptation of the original work provided appropriate credit is given to the original author and the conditions of the license are met.