• We investigate the characteristics of the authors of Tweets containing suicidal intent or thinking, through the analysis of their online social network relationships and interactions. • Results show a high degree of reciprocal connectivity between the authors of suicidal content when compared to other studies of Twitter users, suggesting a tightly-coupled virtual community. • Analysis of the retweet graph identified bridge nodes and hub nodes connecting users posting suicidal ideation with users who were not, suggesting a potential for information cascade and risk of possible ‘contagion’. • Retweet graphs of suicidal content exhibit an average shortest path similar to that of a large comparison network, demonstrating large scale information propagation in small-scale networks.

The World Wide Web, and online social networks in particular, have increased connectivity between people such that information can spread to millions of people in a matter of minutes. This form of online collective contagion has provided many benefits to society, such as providing reassurance and emergency management in the immediate aftermath of natural disasters. However, it also poses a potential risk to vulnerable Web users who receive this information and could subsequently come to harm. One example of this would be the spread of suicidal ideation in online social networks, about which concerns have been raised. In this paper we report the results of a number of machine classifiers built with the aim of classifying text relating to suicide on Twitter. The classifier distinguishes between the more worrying content, such as suicidal ideation, and other suicide-related topics such as reporting of a suicide, memorial, campaigning and support. It also aims to identify flippant references to suicide. We built a set of baseline classifiers using lexical, structural, emotive and psychological features extracted from Twitter posts. We then improved on the baseline classifiers by building an ensemble classifier using the Rotation Forest algorithm and a Maximum Probability voting classification decision method, based on the outcome of base classifiers. This achieved an F-measure of 0.728 overall (for 7 classes, including suicidal ideation) and 0.69 for the suicidal ideation class. We summarise the results by reflecting on the most significant predictive principle components of the suicidal ideation class to provide insight into the language used on Twitter to express suicidal ideation. Finally, we perform a 12-month case study of suicide-related posts where we further evaluate the classification approach - showing a sustained classification performance and providing anonymous insights into the trends and demographic profile of Twitter users posting content of this type.

Dynamic life cycle assessment (LCA) integrated with digital twin technologies is emerging as a transformative approach to evaluating and managing environmental performance in the built environment. This study presents the Building Life-cycle Digital Twin (BLDT) framework-a novel methodology that combines real-time data from Internet of Things (IoT) devices, machine learning algorithms, and semantic interoperability to deliver dynamic, predictive, and high-resolution LCA for construction and infrastructure systems. The framework, developed within the Computational Urban Sustainability Platform (CUSP), addresses the limitations of traditional static LCA by enabling continuous, data-driven sustainability assessments. Incorporating predictive modelling, BLDT empowers stakeholders with timely insights into energy use, emissions, and health and safety performance, supporting proactive environmental decision-making. Validated through a case study at the Port of Grimsby, the BLDT framework facilitated a 25% reduction in energy consumption while enhancing operational efficiency. These results demonstrate the model's potential to support decarbonisation strategies, regulatory compliance, and long-term planning in the construction sector. By operationalising dynamic LCA through digital twins, this research contributes to the advancement of real-time sustainability analytics and resilient urban development.

The recent adoption of building information modelling (BIM), and the quest to decarbonise our built environment, has impacted several segments of the supply chain, including design and engineering practitioners, prompting the need to redefine the construction personnel positions along with associated skills and competencies. The research informs ways in which practitioners can fully embrace the potential of BIM for energy efficiency to promote sustainable interventions by improving existing training practices and identifying new training requirements as BIM evolves and as practitioners’ ICT (Information and Communications Technology) maturity levels improve. This is achieved by adopting a novel text-mining approach which analyses social media alongside secondary sources of evidence to establish a level of correlation between BIM roles and skills. The use of ontological dependency analysis has helped to understand the degree of correlation of skills with roles as a method to inform training and educational programmes. A key outcome from the research is a semantic web-based mining environment which determines BIM roles and skills, as well as their correlation factor, with an application for energy efficiency. The paper also evidences that (a) construction skills and roles are dynamic in nature and evolve over time, reflecting the digital transformation of the Construction industry, and (b) the importance of socio-organisational aspects in construction skills and related training provision. Graphic