Contribution of artificial intelligence AI to construction project management processes State of the

Abstract

Keywords: Artificial Intelligence (AI); Construction Industry; Construction Management; Project Management; Scoping Review

Introduction

Construction 4.0 that involves the use of new technologies [1], has changed the collaborative communication in AEC industry by enabling real-time communication. For

example, Wang et al. noted that the adoption and use of new technologies have led to reduced revisions [2], more accurate decisions, and improved quality of work. Beier et al. highlighted the production of systems that facilitate

*Corresponding author. *E-mail address: haladag@yildiz.edu.tr This paper was recommended for publication in revised form by Editor-in-Chief Ahmet Selim Dalkilic Published by Yıldız Technical University Press, İstanbul, Turkey Copyright 2021, Yıldız Technical University. This is an open access article under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Sigma J Eng Nat Sci, Vol. 42, No. 5, pp. 1654−1669, October, 2024

real-time communication among company personnel using Internet connections [3]. At this point, as a component of Construction 4.0, Artificial intelligence (AI) has also emerged as a new solution to tackle common challenges faced by the industry [4, 5] such as design problems, delays, and contract disputes. Project management processes and approaches will also change as AI applications become widespread [6]. Considering the possible contributions that AI promises for more efficient project management, practitioners need to better understand the potential benefits of AI in construction project management processes. Within this background, this study aims to investigate existing practices and acquire basic information on artificial intelligence in the construction industry to better understand the relationship between the two. In line with this aim, this study reveals the potentials of using AI in the AEC industry through a scoping review, identifies the application areas of AI in construction project management processes, and provides preliminary information for future studies. In literature, many authors have conducted literature reviews to determine the future potential of AI [7-11]. For example, Pan and Zhang conducted a bibliometric review to explore the use of AI in modeling, predicting, and optimizing problems throughout the lifecycle of construction projects [9]. This study covers all processes of construction projects from a broader perspective. In a different research endeavor examining the application of artificial neural networks in the field of construction management, Xu and colleagues offered a comprehensive overview and categorized the research articles based on different criteria [12]. Although these studies seem to have overlaps in classification, this study differentiates from prior studies within its scope since it scans all the methods of artificial intelligence, addresses both the positive and negative results of these technologies, and provides a guide to the potential of future studies based on this information, as well as scanning the latest literature on the subject in a holistic way. Contrast to existing literature reviews on AI use in project management domain, this study aims to detect application areas of AI in construction project management processes by using scoping review method and create a base for the development of theories that can support future studies. In line with the scope of the study, after the introduction section, section 2 presents the importance of using artificial intelligence (AI) in project management. In section 3, the methodology of the study and its steps are then elaborated upon. In this section, research questions and the boundaries of the publications are determined. General information obtained from the scoping review is processed. Findings derived from scoping review analysis are addressed in Section 4. This section consists of the presentation of key application areas of AI in construction project management, research trends and identified gaps and justifications based on the scoping review findings. Finally, Section 5 concludes the study by stating practical and theoretical

implications, and Limitations and Directions for Future Research for further studies. Importance of Artificial Intelligence (AI) Use in Project Management The history of AI dates to 1950, when the British mathematician Alan Turing posed the question of whether machines could think. After experiencing ups and downs over the course of 60 years, AI has regained technological importance due to rapid developments in computing, big data, artificial neural networks, deep learning, and other new technologies [13, 14]. AI is a computer system that perceives visual perception, recognizes speech, and can translate between languages. It is used to solve complex decision-making processes that cannot be solved directly with mathematics by understanding project information and the project environment [15]. Machine learning is a subset of AI, using algorithms and statistical models to learn from data and make decisions [16, 17]. With the advancements in machine learning and big data technologies, AI has become a major technological opportunity in the world. The potential of this technological advancement also triggers the need for AI use in AEC industry. On a limited scope, the need for AI use in construction arises from the desire to improve cost management, enhance quality control, increase efficiency and productivity, and address complex issues in project management. The potential areas that AEC industry can benefit from AI use explained in detail in below: • Empowering project managers in decision-making processes by leveraging data processing and utilization: In AEC industry, as the construction projects become more complex and large-scaled, the number of participants and the volumes of construction data including project plans, schedules, and performance metrics start to increase. In this regard, AI stands out as one of the digital technologies with significant potential to leverage the vast amount of available big data for problem-solving and enhancing decision-making within the field of construction management [18-20]. By applying machine learning algorithms, AI can identify patterns, trends, and insights that can inform decision-making, optimize resource allocation, and improve project outcomes. As it can be seen, artificial intelligence has the capability to offer continuous real-time monitoring and analysis of construction operations, enabling project managers to make well-informed decisions promptly based on data. This improves not only project control, reduces risks, and enhances overall project performance but also prevents poor decision-making through the project management processes. • Increasing productivity and efficiency: Considering that AEC industry is already criticized because of efficiency and productivity issues [21], incompetency in data analytics might imbricate these efficiency and productivity issues. AI technology can improve work

Sigma J Eng Nat Sci, Vol. 42, No. 5, pp. 1654−1669, October, 2024

efficiency and standards by changing the required human resources for construction-related jobs [14]. AI can automate repetitive and time-consuming tasks, such as data entry, document management, and project scheduling. This allows construction professionals to focus on more complex and value-added activities and result as increase in overall efficiency and productivity. AI can also enable the use of autonomous equipment and robotics in construction, reducing the need for manual labor in repetitive or dangerous tasks. This can lead to increased productivity along with improved safety, and cost savings. Sustaining project success: The use of AI in AEC industry also has a vast number of potentials in sustaining project success. Project success is mainly defined by the project management triangle, consisting of time, cost, and quality pillars [22]. Planning a project is one of the most important processes in project management, but the importance of planning software needs to be investigated [23]. Construction cost control is crucial, as delays in any stage of the project can cause cost overruns due to increased workmanship, working time, or material usage [24]. AI has the potential to forecast cost overruns by considering project scale, contract type, and the competence of the project manager [25]. AI can also support investment decisions by accurately estimating the cost of construction projects, which can help reduce project implementation costs [26]. Predictive models that utilize historical data, such as planned start and end dates, can be used to create realistic timelines for future construction projects [22]. By implementing AI in construction scheduling, managers can monitor schedules more efficiently by estimating the completion and delay times of construction projects [27]. AI can be applied in real-time, enabling project managers to swiftly and knowledgeably decide how to allocate resources as the project unfolds [28]. This can help prevent project delays and lead to more realistic timelines for future projects. Furthermore, AI can provide a clear and realistic view of construction site activities to top-level management and engineers, which can lead to improvements in construction efficiency and quality [14]. AI can also analyze data from various sources, such as sensors and cameras, to monitor construction quality in real-time. It can identify defects, deviations from specifications, and potential issues, enabling early intervention and improving overall quality control. Anticipating occupational accidents and equipment-related safety issues: Safety represents a paramount and indispensable aspect of the construction industry. AI can be used to anticipate occupational accidents and equipment-related safety issues that may arise during construction projects [25]. AI-powered technologies (such as drones, robots, and wearable technologies) can be used for site inspections, monitoring hazardous areas, identifying potential safety risks, and monitoring

workers’ behavior. AI algorithms can analyze real-time data on-site from sensors to detect unsafe conditions, helping to prevent accidents and improve safety on construction sites [20]. Additionally, pattern recognition-based AI technologies are being used for data and system integration for enhancing safety management. When paired with virtual reality, these technologies become even more potent as they assure real-time personnel safety. Providing insights for project managers to quickly prioritize potential risks and identify proactive actions: As the main field of construction management, AI can monitor, recognize, evaluate, and predict potential risks in terms of safety, quality, efficiency, and cost across teams and work areas even under high uncertainty [29, 30]. AI-based risk analysis can provide insights to help project managers quickly prioritize potential risks and identify proactive actions rather than risk mitigation responses [9]. Machine learning and natural language processing are being applied in construction for risk detection and assessment to issue early warnings [20]. Consequently, AI is expected to play a significant role for project managers in risk assessment, generating decision support, automation of risk monitoring, and simulation and scenario analysis. Additionally, AI technologies, such as Building Information Modeling (BIM) and virtual reality allow for better visualization, clash detection, and coordination among different disciplines, reducing errors and rework during construction.

In brief, the novelty of AI systems in the construction industry lies in their ability to leverage advanced technologies, data analysis techniques, and automation to address specific challenges and improve efficiency, productivity, safety, decision-making, and overall project outcomes. AI systems bring new capabilities, insights, and efficiencies to the construction industry, enabling practitioners to leverage data-driven intelligence for better project execution. By embracing AI technologies, the AEC industry can drive innovation, increase productivity, supports decision-makings arise from complex project management challenges, and achieve better project outcomes. Along with these contributions that artificial intelligence will provide to project management, there has been a notable rise in research on the application of artificial intelligence in the construction industry. It is evident from the literature that the use of AI techniques in the construction industry has become a trending topic. The researchers also discussed many different AI methods for construction project management. The practical implementation of AI applications has led to positive outcomes in project management processes, indicating that the technology will continue to evolve. As the amount of data in the construction industry grows, the use of AI is expected to become more prevalent, given its reliance on data processing and utilization.

Sigma J Eng Nat Sci, Vol. 42, No. 5, pp. 1654−1669, October, 2024

Consequently, AI is expected to play a significant role in the industry’s future. Research methodology The use of AI in the industry has vast potentials. Thus, it is imperative to know the future of artificial intelligence in construction project management processes. With this background, this study aims to identify research trends in this area while determining the role of artificial intelligence in the construction industry. In line with this aim, the scoping review method was adopted. Literature review methods encompass a range of tools available to researchers, and there isn’t a single universally “perfect” type of literature review. Scoping is one type of literature review method. However, there are some differences with a systematic literature review. While a systematic literature review focuses on well-designed questions, there is no need to specify a clear question, as the different topics covered in scoping studies will create broader issues. A systematic literature review provides clear answers and seeks answers to specific research questions. For this reason, answers to questions are sought rather than evaluating the included studies [31]. At this point, it should be noted that the scoping review technique differs from the systematic review technique. Scoping reviews provide a broad view of the evidence on issues. In this way, emerging areas are examined, and basic concepts are explained. It also enables the identification of gaps in the literature [32]. Since scoping studies do not provide detailed information about the method of analysis consistent with their own logic, there is not enough information about the way scoping studies are conducted [33]. The reliability of the findings has increased as the study contains details that can be replicated by someone else and refutes the judgment that the study lacks methodological rigor since it did not perform a “systematic” review [34]. When utilizing the scoping review method, it’s essential to follow a series of stages, including determining the research question, identifying relevant studies, selecting the studies, creating data visualizations, and summarizing and reporting the results in a concise manner respectively [31]. On the other hand, literature searches are accelerated by keyword searches created by research questions [7]. The research questions of this study are expressed in the next section. Determining the Research Questions The research questions addressed by this study are as follows: • What are the key application areas of AI in construction project management? • What are the research trends in AI technology usage in the AEC industry? • What are the literature gaps and justifications related to AI use in AEC industry? • What are the potential future applications of AI use in the AEC industry?

Identification of Related Studies The selections are limited to studies between 2012 and 2023 in terms of containing the current literature. Databases used for searching are the American Society of Civil Engineers (ASCE), IEEE Xplore Digital Library, Web of Science (WOS), and Scopus. The keywords used for searches are “deep learning” “machine learning” or “artificial intelligence” and “construction management”. Since most of the literature in the selected databases is in English, searches were also made with English keywords. Selection of Studies The inclusion or exclusion criteria of the studies were carried out to determine the effects of machine learning from artificial intelligence applications on construction projects were selected in relation to the nature and quality of the studies. Since the subject of artificial intelligence is based on a technological development that has been focused on in recent years, the time frame has been limited to between 2012 and 2023 to keep up with current studies. Older studies were excluded, assuming that before these dates the subject was studied with old, incomplete, or insufficient equipment. It is envisaged that the latest developments in the literature, including the subject, will be discussed with a selection of current studies. The exclusion criteria are limited to excluding other studies that are not closely related to the subject in question. Since machine learning is known to serve interdisciplinary issues, the studies discussed were directly or indirectly related to the architecture, engineering, and construction industries. Studies that do not meet these conditions are excluded. Figure 1 shows the literature search strategy.

Sigma J Eng Nat Sci, Vol. 42, No. 5, pp. 1654−1669, October, 2024

Graphing the Data In this section, a total number of 41 studies obtained through literature review were analyzed. “Table A1. Summary findings of selected articles” in “Appendix” presents the 41 studies with their key findings whereas “Table A2” in “Appendix” presents the classified application areas of artificial intelligence technologies in reviewed articles. Compilation of Results According to the findings of studies, application areas of artificial intelligence technologies in project management processes are classified under eight main topics: cost management, time management, quality management, safety management, risk management, contract management, dispute management, and sustainability. The compilation of results shows that the majority of the studies deal with the subject of “time management” (a total number of 18 studies out of 41), whereas “cost management” comes in second place with 16 studies. The least directly addressed issue was “sustainability,” with a total number of 3 studies. Evaluation of Findings In line with the aim of detecting application areas of AI and creating a base for future studies on AI applications in construction project management processes, results gathered from the scoping review method were presented in three main sections: “Key application areas of AI in construction project management”, “Research trends”, and “Identified gaps and justifications”. Key Application Areas of AI in Construction Project Management Detailed evaluations regarding the eight main application areas of AI technologies on construction project management processes can be found below: i) AI use in cost management Artificial intelligence helps many researchers make the necessary decisions for the control of budget overruns in construction projects considering controlling project expenses is important in cost management [35]. The use of artificial intelligence reduces costs by providing savings, so it can be argued that the integration of artificial intelligence is beneficial to project construction processes. For example, computer vision [36], reducing chaos is possible [29]. The reviewed literature shows that the success of AI-powered tools in determining cost trends is clear. In this way, benefits such as joint budget tracking, resource optimization, and quality control can be achieved in projects. When the studies on the application of AI to the efficiency of cost management were examined, Boosting and Adaptive Boosting (AdaBoost), Extreme Gradient Boosting (XGBoost), Stochastic Gradient Boosting and Decision-making systems are amongst the most preferred AI tools for the development of cost estimation models in construction.

ii) AI use in time management Since time management is one of the three main pillars of project success [37, 38], the importance of providing time management based on artificial intelligence applications is increasing. Project managers’ work can be facilitated by estimating potential delays in projects by making predictive scheduling with the algorithms to be developed. The allocation process of resources can be managed, and automatic progress can be tracked. For example, pre-construction projects should contain reliable projections of project duration [39]. The problems created by the data collection method used in traditional methods consisting of grueling actions such as field visits are facilitated through systems established with analytical platforms [40, 41]. For example, with systems using GPUs, computations are improved, and the adoption of new technologies is increased [42]. On the other hand, the problem of reducing competitiveness is caused by the unpredictability of the project duration at the tender stage, disagreements between the contractors and the property owners [43], the length of the problem-solving period of the projects, and the length of the time required for data processing [44]. When the studies on the application of AI to the efficiency of resource allocation, and planning were examined, the following AI tools come to forefront: Machine Learning algorithms, and Convolutional Neural Network (CNN) for planning and scheduling of construction projects, Artificial Neural Networks (ANN) for estimating durations and for establishing a link between logistic resources allocated to a construction project and program success, Discrete-event simulation (DES) for improving foresight method in the optimization of planning and scheduling. iii) AI use in quality management The use of AI is a promising tool for quality management in AEC industry. Because what is desired in quality management is quality management systems that document and monitor quality information [45]. However, experts have associated the lack of adoption of new technologies in the construction industry with poor quality performance [46]. Within this perspective, studies reveal that AI can be a helpful tool in identifying potential quality problems in projects [18], providing effective data management [47], automating scheduling in project processes [48, 49], making quality and efficiency calculations in projects [7], improving the skills and expertise of project stakeholders [9], obtaining fast and accurate results by automating tasks, increasing quality and productivity [49, 50], and obtaining the necessary information to meet the quality and safety objectives of projects with object detection [51]. AI can also be used to improve construction project delivery quality by integrating technologies such as BIM and 4D CAD [52]. iv) AI use in contract management The rights of construction stakeholders and the determination of these rights depend on the contracting stages

Sigma J Eng Nat Sci, Vol. 42, No. 5, pp. 1654−1669, October, 2024

of the projects. For this reason, processes are facilitated with a platform where contract management can be facilitated [53]. There are researchers who have developed this and similar platforms in the literature. Choi et al. have developed an artificial intelligence algorithm module that performs automatic risk extraction to identify risk items and detect and manage risky statements while preparing construction contract documents [54]. Authors used AI and text mining to develop a risk analysis tool for analyzing contractor’s risk in invitation to bid in EPC projects. v) AI use in dispute management Conflicts in construction projects affect the quality of construction and the interests of the parties [53]. Various technologies supported by artificial intelligence have been used to prevent these problems. For example, Chou et al. used artificial intelligence technology for the early detection of conflicts in public-private partnerships and proposed a model that provides a warning by detecting possible conflicts [55]. An efficient model has been developed using Fast messy generic algorithm (FPGA)-based SVM for the estimation of possible conflicts in public-private partnership projects. According to the study of Gao and Sun, conflicts in construction projects arise from different understandings of the rights and obligations of the project parties in the process [53]. Weak legal awareness of the parties, unclear rights and responsibilities in the contract, uncertain terms, and even the absence of the contract in some cases create various project conflicts. The artificial intelligence-supported platform they have developed takes part in the resolution of disputes as a “fourth party” in the resolution of contractual disputes in construction processes [53]. vi) AI use in risk management (uncertainty/forecast) Construction project stakeholders face many risks due to contracts [18]. Studies in the literature show that these risks can be managed with a digital risk analysis tool based on artificial intelligence and data mining [54]. Construction cost estimation, building energy system behavior estimation, short-term building cooling load estimation, building design energy estimation, compressive strength and crack estimation of recycled concrete, long-term electrical and heating load estimation, and heavy equipment parameters estimation can be made with artificial intelligence [5]. Artificial intelligence applications can be used to prevent risks by prioritizing risks at the project site, which helps the project team focus their resources on the biggest risk factors. Prevention of conflicts between stakeholders by identifying them before the project and estimations of the resolution of these conflicts in cases where there are disagreements can be realized by machine learning methods. When the studies on the application of AI to the efficiency of risk management were examined, the following AI tools come to forefront: machine learning algorithms capturing complexity-risk interdependencies, CBR to evaluate the cyclical risk management of construction projects that have

inherent risks, decision tree and Naïve Bayesian classifiers for facilitating accurate project delay risk analysis and estimation. vii) AI use in safety management Construction safety is a necessity in terms of people and money. Artificial intelligence techniques provide a safer environment by removing construction personnel from dangerous and poorly constructed environments [56]. Worker deaths and injuries caused by inadequate safety measures in construction processes can be resolved with the new occupational safety system, an online monitoring technology based on the approach of detecting the falling probability of workers working in high-rise buildings [57]. With artificial intelligence, the detection of the security guard, the detection of the protective equipment of the worker, and the postural evaluation of the employees can be done [5]. Liu et al. reviewed articles using computer vision technologies to ensure construction safety and supported the use of this integration [51]. Reviewed papers using computer vision technologies to ensure construction safety generally focus on the implementation of AI tools such as machine learning algorithms, CNN, SVM, ANN, k-Nearest Neighbors (k-NN), Regions with Convolutional Neural Network (R-CNN) and Region-based fully Convolutional network (R-FCN) to support the use of AI in this application area. viii) AI use in sustainability To prevent the damage caused by construction waste to the environment, artificial intelligence applications that helps post-construction waste management by determining the technique to be applied to construction waste can be used [58]. But the number of studies in which artificial intelligence has been applied in construction waste management has been found to be limited. This may be because AI focuses more on off-site applications of project management processes and deals with contracting processes. On the other hand, sustainability is not just about waste management. Ending a process with less expense, less time and more effectiveness than before also contributes to sustainability. In addition, thanks to the integration of artificial intelligence applications into projects, reducing the number of employees and the use of labor and carbon consumption will also support sustainability. In this respect, almost all AI use cases indirectly support sustainability. The exception here is that the high-capacity computers and power usage required by AI will be viewed negatively in terms of sustainability alongside all their technological and economic benefits. Research Trends While there is evidence of resistance to technological innovations in the AEC industry, the benefits of digitalization should also be acknowledged. Current studies indicate the need for further work on key plans that will facilitate the adoption of technology and address sustainability

Sigma J Eng Nat Sci, Vol. 42, No. 5, pp. 1654−1669, October, 2024

and quality management aspects in project management. Additionally, evaluations of the applications of artificial intelligence technologies in construction project management processes suggest that research trends will increasingly embrace the use of AI. Furthermore, despite extensive research on cost and time management, ongoing efforts are being made to explore these processes using advanced machine learning methods. The researchers discussed many different AI methods for construction project management. Researchers have discussed proposals for the use of artificial intelligence for construction project management using many AI tools such as Artificial Neural Networks (ANN), Deep Neural Network (DNN), Convolutional Neural Network (CNN), and Recurrent Neural Network (RNN). One commonly used artificial intelligence technique in the context of construction project management is supervised learning, which is a machine learning method. In supervised learning, the classes of data used for training the AI are predetermined. Examples of this method include KNN, SVM, ANN, DT, and NB. Another machine learning method is deep learning, which has gained prominence with the advancement of technology and the utilization of powerful machines. In the field of construction project management, the use of deep learning is observed through methods such as CNN and RNN. The selection of these methods is aimed at continuously updating the systems and considering past information to achieve better evaluation and results. Identified Gaps and Justifications The AEC industry is considered as an industry that resists the acceptance of technological innovations. Although the studies examined re-expressed the existence of this resistance and listed the benefits of digitalization to the sector, the amount of work on key plans that will ensure the adoption of technology is limited. On the other hand, the fact that most of the work focuses on cost and time management can show that the most important issue in construction work is time and financial income. However, when the project management triangle (time, cost, and quality) is considered, it is seen that the quality features of the projects are also very important. For this reason, it is expected to increase the number of studies on the use of artificial intelligence applications in quality improvement initiatives related to construction project management. In general, it is seen that the use of “dataset”, which artificial intelligence technology requires by its nature, is rare. Datasets are difficult to obtain, especially in construction project management, because project stakeholders tend to keep their information confidential. However, when the project stakeholders do not provide a data set for researchers, studies on the transition to the digitalization process will not be developed. For this reason, it is necessary to increase the amount of publicly available datasets that will enable the use of artificial intelligence in the construction industry.

Furthermore, decisions made in the AEC industry are related to experience gained based on past experiences. However, artificial intelligence applications used today cannot cope with the accumulation of knowledge based on human experience [57]. Thus, more attention should be put based on AI use in a broader range of project management contexts especially by using specific case studies and historical data with real-world scenarios.

Conclusion

This study was conducted to identify AI application areas in the project management process. A scoping review method was adopted to analyze 41 papers published between 2012 and 2023, which were classified under eight main application areas: cost management, time management, quality management, contract management, dispute management, risk management, safety management, and sustainability. The findings indicated that there are limited studies on quality management compared to time and cost management in terms of project success triangle. It is notable that “sustainability” and “dispute management” are the least researched areas of artificial intelligence applications in project management. Implications For Researchers The study presents how AI’s role in construction has been addressed by researchers and highlights the research trends by showing ongoing efforts in using advanced machine learning methods. Within this respect, this study that addresses the research trends and current applications of ground-breaking technology in project management processes provides theoretical contribution researchers by mapping the current interest related to artificial intelligence studies. Implications for Construction Industry Construction practitioners should identify their company’s pain points and areas where AI can have the most significant impact. Once pain points are identified, practitioners should explore available AI solutions that address those specific needs. There are numerous AI technologies and tools tailored for the construction industry, including project management software, predictive analytics, computer vision, natural language processing, and robotic automation. Evaluating and selecting the right AI solutions is crucial for successful implementation. The findings of this study might shed light to crucial areas where they can prioritize their investment where AI can have the most impact on their company’s unique needs. Additionally, AI is a rapidly evolving field, and practitioners should stay updated on the latest advancements and innovations. Another contribution of this study for practitioners is enabling practitioners updated on AI advancements by reveal important insights on AI use in project management processes.

Sigma J Eng Nat Sci, Vol. 42, No. 5, pp. 1654−1669, October, 2024

Limitations and Directions for Future Studies While this study presents potential benefits of AI use into project management domain and the state-of-theart of AI-based studies with scoping review method, it is essential to recognize its limitations. Since this study is a review paper, it has the limitations based on the selection of studies within scoping review. Since machine learning is known to serve interdisciplinary issues, the studies that were not directly or indirectly related to the architecture, engineering, and construction industries were excluded. Another limitation involves language selection. The studies that were subject to our analysis were selected only from the studies in English. According to the results obtained from the findings, the usage areas of artificial intelligence in project management are increasing day by day in academic terms. However, a limited study on AI use in sustainability and dispute management were detected. Thus, this study recommends further emphasis on sustainability and dispute management, as these areas have been covered by relatively few publications. Future research can focus on exploring the use of AI in dispute management and addressing sustainability issues in construction project management. On the other hand, traditionalism and not following technological developments, which are two of the dominant features of the AEC industry, prevent the use of artificial intelligence tools in the field of project management in the sector. In addition, the number of samples to be studied by researchers who want to conduct research on this subject is limited. Therefore, future studies can focus on developing key plans that facilitate the adoption of AI technologies in the construction industry. These plans can address the challenges and resistance to technological innovations, promoting the integration of AI tools in project management processes. Additionally, for facilitating the use of AI in the construction industry, future efforts should focus on increasing the availability of publicly accessible datasets. This will enable researchers to develop and test AI algorithms and models for construction project management. In brief, future research should aim exploring AI use sustainability and dispute management domains, overcoming resistance to technology adoption, and expanding the availability of datasets for AI applications in construction project management.

Nomenclature

Adaptive Boosting Architecture, Engineering, and Construction Artificial Intelligence Artificial Neural Networks The American Society of Civil Engineers Case-Based Reasoning Convolutional Neural Network Deep Neural Network Decision Tree

Engineering, Procurement and Construction Fast Messy Generic Algorithm The Institute of Electrical and Electronics Engineers Web of Science K-Nearest Neighbors Naive Bayes Regions with Convolutional Neural Network Region-based Fully Convolutional Network Recurrent Neural Network Support Vector Machines Extreme Gradient Boosting

Data Availability Statement

The authors confirm that the data that supports the findings of this study are available within the article. raw data that support the finding of this study are available from the corresponding author, upon reasonable request.

Conflict Of Interest

The author declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.

Ethics

There are no ethical issues with the publication of this manuscript.

Share and Cite