Recently, there has been a growth in the research interest on applied machine learning (ML) in safety analysis in the construction industry. The increased interest is part of a search for improved prevention of occupational accidents with a focus on text analysis and natural language processing (NLP). However, ML-based approaches have been less adapted compared to their perceived benefits due to barriers of implementation and challenges in analysing safety records in the construction sector. And the current literature has been criticized for a lack of clarity around the description of methodologies, interpretation, and the context of the application. Therefore, this work aims to review the latest developments in research applying ML to accident report analysis in construction. A review of the published literature on ML-based analysis of construction accident reports was carried out and organized in terms of the data pre-processing, algorithms, testing and implementation and further organized based on data structure. The results of the review found limitation related to data availability besides the manual structuring and the less use of unsupervised learning reflect complexity of handling textual accident data. Moreover, types of accidents happen in proportionally varying frequencies and need careful tackling outside basic assumptions of data pre-processing in addition to the general need for data pre-processing comparative studies and automated pipelines. The review also showed that data mining (DM) and unsupervised learning were less used especially with semi-structured and unstructured datasets reflecting maybe inefficient natural language processing (NLP) application with these types of learning. Among the reviewed articles, only four out of six prototypes were externally validated on construction environment thus we propose that future efforts would benefit from incorporating a standardized development method that also explicit how ML safety recommendation informs decision making. Future research should experiment and ascertain different choices in the pre-processing stage, validating the performance of the ML models and implementation in the construction practices. Finally, there are more advanced NLP methods that could be applied if domain specific repositories were available such as relation extraction and there are various advances that could be explored including large language models (LLMs). © 2005 The author(s).

Artificial intelligence (AI) is in need for a framework that balances the opportunities it represents with its risks. But while there is a broad consensus on this, and public regulative initiatives are taken; there is far less knowledge about how these dilemmas/opportunities/risks are played out in practice. The interest into ethics in organisation driven by a discourse on “Trustworthy AI”; makes us wonder whether an ethical approach to AI in organisation is purposeful; or needs modification. We investigate this by viewing the development and use of AI as structuration of practices. The empirical material is our own development of an AI system. Using studies of ethics in moral engineering design; AI is a question of structuration processers with unintended consequences. It is a “slide” from ethics of virtue to ethics of benefit as corroborated by engineers/designers referring ethical dilemmas to managers and politicians. The EU framework of Trustworthy AI for designing and using more accountable AI systems - considering ethics; human autonomy; harm prevention; fairness etc., conflicts with contemporary construction organisations. We propose an extension of the EU guidelines. © Association of Researchers in Construction Management

Occupational accidents are an urgent problem in construction. Machine learning (ML) methods for analyzing large amounts of data and the availability of accident report data have generated aspirations for novel learnings. Yet the quality of data in terms of input, inner availability, and output occurs as an issue in many ML development projects. This paper aims at investigating strategies to define, understand, and tackle poor data quality in a contracting company's accident reports. A selective literature review within software system data quality and ML shows different foci on external or internal data. A set of records of occupational accidents are then analyzed. There are many missing entries on causality, as well as shallow descriptions, which hinder the discovery of new risks - possibly due to the data collection format and procedures. The low number of full entries calls for new repair strategies - both externally and internally. © ASCE 2023.All rights reserved.

Approaching quality inspection plans in Swedish construction projects as mere checklists and minimizing the clients’ involvement, can reduce their value. We propose improving this process through a general cloud service concept for clients, designers, and contractors, utilizing generative pre-trained transformers (GPTs). Methodologically, we synthesize literature insights on GPT uses for construction, and empirical inquiries on developing a quality self-inspection service. We posit that through such a service, project knowledge, known quality defects and lessons-learned from previous cases can be better accessed and shared – potentially leading to time savings, suggesting best practices, and improving the collaboration among clients, designers, and contractors. © 2024 European Council on Computing in Construction.

The transition to a society with low emissions has led to several intensives for decreasing operational energy and the environmental impact of buildings. The embodied impacts from manufacturing materials have been shown to increase in relative importance as the operational energy efficiency has increased. Several case studies have shown various technical solutions which can reduce embodied carbon emissions. But is this reduction good for business? There are several building projects that have achieved low embodied emissions, but these are often in segments of premium private clients or green public procurement where additional motivation such as reputation and long-term viability is in place. However, with the transition to a low emission society, there is a need to include all types of building markets. This study aims to find business model innovation opportunities with reduced embodied emissions in building projects where the clients have low motivation beyond reducing costs. The approach is through action research with a Norwegian contractor seeking new opportunities while keeping the main competitive advantage. The research starts with a case that could reduce overall greenhouse gas emissions, and includes the potential savings from green loans to find potentials to capture value from reducing emissions. The results show that criteria exist for green loans based on reducing operational and embodied emissions. Future studies are however need to make an integrated assessment on the potential value captured from these green loans. © Published under licence by IOP Publishing Ltd.

This paper explores institutional forces in sustainability reporting (SR) practice, adopting an institutional field approach to an emerging field of sustainable real estate reporting of sustainable investments through the EU taxonomy, over-layering the mature exchange field of the real estate business. We study 29 listed real estate companies in Sweden and their process towards the first taxonomy reporting spring 2022. Three companies are obliged to report their future coverage of the legislation, while 14 report voluntary and 3 choose to report their degree of sustainability, thus showing clear elements of an emerging institutional field, and its active dynamics even where law is not obligatory. Similarly, the companies’ status of sustainability was evaluated from 2022 and previous years’ annual reports, shows that 16 appear to follow each other closely, 9 companies attempt to take a leading position while only 2 appear to attempt to downplay sustainability. Annual reports tend to have a character of mechanical compliance where new insight produced by taxonomy reporting is merely juxtaposed to other reporting standards, such as Greenhouse Gas Protocol. Only one company appear to attempt to establish crosscutting learning from the many sources of evaluation the different standards and legislation represent. Moreover, legislation is likely to have limited effect as the real estate companies are only limited dependent of Bank loans, having a series of other financial means at their disposal. Many companies also had their strongest financial year in 2021 and the timing of the arrival of a financial control instrument is less opportune. 

Industrialised Housebuilding (IH) in Sweden have grown within Multi-Storey Housing made of Timber (MSHT) and most of the producers rely on this approach. Business models for Industrialised Housebuilding, often start with prefabrication. With the rapid growth of sustainability demands and circular construction as an uprising theme, a central question is, what is the sustainability element in Swedish industrialized housebuilders business models regarding MSHT? Sustainable transition theory is adopted. The method is a desk study of existing research, websites, annual reports and other material. The sustainability element in the business models of industrialized house builders is explored, with focus on circular construction. MSHT is described as reducing environmental impact compared to concrete and provides social values, enabling its diffusion, however with less apparent cost advantages. However, with the growth of circular thinking, IH may have potential to further develop. The findings show that sustainability is overall present in the development of IH within MSHT, where the companies show a homogenous picture with varying challenges and contribute to sustainable transition. Regarding circular construction, the study shows potential in additional steps needed from a life-cycle perspective. © 2021 Proceedings of the 37th Annual ARCOM Conference, ARCOM 2021. All Rights Reserved.

Construction equipment emissions in civil engineering are a major sustainability issue. However, the industry continues investing in diesel (and/or biodiesel) machines - which, even if compliant with EU regulations, are far from "clean". Cleaner technologies in construction equipment, like electrical engines, are considered more expensive investments; moreover, they are dependent on the available power supply while operating in confined areas. So, transitioning these machines sustainably involves changing technologies, business models, and public regulation. In Scandinavia, heavy-duty engines (over 25 tons) have only recently become (limitedly) available. Therefore, the current paper analyzes enablers and barriers for a sustainable transition of civil engineering construction equipment to onsite electrical machines in Scandinavia. The sustainable transition theory, combined with sustainable business models, serves as the framework of understanding. Empirically, a desk study of governance and regulation is combined with material from four fossil-free test building sites in Norway, Denmark, and Sweden. The results highlight the importance of a public-private business model, where public client-driven transition is subsidy-supported (e.g., making electrical equipmentavailable through concession, and encouraging small innovative machine manufacturers to develop electrical equipment), while waiting for international construction equipment players to become transition-ready. Recommendations for the transition thus include strengthening public-private collaboration. © 2021 Proceedings of the 37th Annual ARCOM Conference, ARCOM 2021. All Rights Reserved.