RMIT Europe

Purpose This study examines how digital platforms (DPs) can drive social sustainability (SS) by influencing user behaviour in the context of sustainable mobility. While DPs have been widely discussed for economic and environmental outcomes, their role in fostering SS through user engagement remains underexplored. Design/methodology/approach A behavioural model was developed by integrating the Theory of Planned Behaviour (TPB), Technology Acceptance Model (TAM) and Equity Theory. This study used a time-lagged survey of 406 users of a DP for SS based in a major city in central in India, which incentivises responsible traffic behaviour. Confirmatory factor analysis was employed to validate the measurement model, and ridge regression was used to test the proposed hypotheses. Findings Attitude, captured through belief- and affect-based evaluations of social responsibility, along with perceived ease of use and effort fairness, significantly predicted intention to use the platform. Social norms were non-significant, suggesting that normative pressure plays a limited role in this mobility setting. Intention, in turn, predicted socially sustainable mobility behaviour. Overall, the results show that users respond more strongly to their own perceptions, usability and fairness than to social expectations, emphasising the personal agentic role of DPs in supporting socially sustainable practices. Research limitations/implications This study opens new pathways for platforms and sustainability research by demonstrating how user engagement can facilitate socially sustainable behaviours through incentivisation, It encourages scholars to expand behavioural models beyond traditional constructs by incorporating perceived fairness, emotional alignment and usability in the digital context. Although limited to one platform and cultural setting, the findings provide a replicable model for exploring user behaviour in digital ecosystems. Future research should adopt longitudinal and cross-cultural designs to assess habit formation, test the framework in varied policy environments and examine how DPs can be co-designed with communities to embed SS into everyday mobility behaviours. Practical implications DPs aiming to promote socially sustainable mobility must go beyond superficial incentives. Designing user engagement strategies that align with individuals’ beliefs and emotions around social responsibility can strengthen behavioural intention. Platforms should ensure that rewards are perceived as fair and proportional to effort, and streamline ease of use to reduce participation barriers. Public–private collaborations can integrate such platforms into mobility governance, using data-driven, user-centred design to complement weak institutional enforcement. By embedding sustainability into everyday interactions, DPs can become powerful tools for shaping long-term, pro-social behaviours in transport and beyond. Social implications This study emphasises the role of DPs as enablers of socially sustainable behaviour. By linking individual actions to collective outcomes through incentives, platforms can foster safer, more equitable mobility systems. The findings highlight the importance of fairness, accessibility and emotional engagement in driving participation, suggesting that digital interventions can build civic responsibility from the ground up. As platforms increasingly mediate everyday life, their design choices hold significant social power, shaping norms, enabling inclusive participation and addressing systemic gaps in public governance and infrastructure through bottom-up engagement. Originality/value The study develops and tests a behavioural framework based on the TPB-TAM-Equity theory in the often-overlooked dimension of SS. The study incorporates the personal agentic role of DPs in influencing SS behaviour in the specific context of sustainable mobility. It goes on to identify drivers of SS behaviour and how designing DPs for SS can use these to address systemic social issues like road safety. The findings enrich platform, behavioural and sustainability literature, and point to practical strategies for DPs.

The application of message-passing Graph Neural Networks has been a breakthrough for important network science problems. However, the competitive performance often relies on using handcrafted structural features as inputs, which increases computational cost and introduces bias into the otherwise purely data-driven network representations. Here, we eliminate the need for handcrafted features by introducing an attention mechanism and utilizing message-iteration profiles, in addition to an effective algorithmic approach to generate a structurally diverse training set of small synthetic networks. Thereby, we build an expressive message-passing framework and use it to efficiently solve the NP-hard problem of Network Dismantling, virtually equivalent to vital node identification, with significant real-world applications. Trained solely on diversified synthetic networks, our proposed model—MIND: Message Iteration Network Dismantler—generalizes to large, unseen real networks with millions of nodes, outperforming state-of-the-art network dismantling methods. Increased efficiency and generalizability of the proposed model can be leveraged beyond dismantling in a range of complex network problems.

Introduction. The rising global incidence of cesarean deliveries has led to elevated abnormal placentation, particularly placenta accreta spectrum (PAS) disorders. These conditions represent serious obstetric complications with high risks for both maternal and fetal morbidity and mortality. А im: to analyze a clinical case of placenta increta with deep invasion, highlighting the diagnostic value of advanced ultrasonographic techniques. Case presentation . A 29-year-old pregnant woman with a history of three cesarean sections (2014, 2017, and 2025) and prominent somatic comorbidities (chronic pyelonephritis and urolithiasis) underwent routine antenatal ultrasound screenings at 8, 12, 20, 23, and 28 +6 weeks of gestation. Standard transvaginal and transabdominal sonographic techniques were used. After sonographic suspicion of placenta increta, magnetic resonance imaging (MRI) was performed for verification. Final diagnosis was confirmed intraoperatively and through histopathological analysis. Ultrasound revealed signs consistent with PAS type 2 (placenta increta): marked thinning of the myometrium, dilated lacunae, retroplacental hypervascularization, and placental bulging. At 28 +6 weeks, transvaginal sonography detected further invasion into the cervical canal (PAS 3a). Color Doppler imaging revealed vascular "rail signs," indicating deep invasion. MRI confirmed complete placenta previa with abnormal tissue growth into the uterine scar and myometrial layers. This case demonstrates the effectiveness of modern ultrasonography and Doppler imaging in the early identification and classification of PAS disorders. Although previous publications emphasized limitations in determining invasion depth via ultrasound, this report highlights its diagnostic reliability, especially when complemented by MRI. Early diagnosis is essential for surgical planning and improving perinatal outcomes. Conclusion . Ultrasound primarily combined with color Doppler imaging, provides a reliable and non-invasive means for diagnosing PAS disorders. In this case, the identification of specific Doppler features – particularly the "rail sign" representing vascular bridging between the myometrium and serosa – proved critical for diagnosing placenta increta. These findings highlight a potential for advanced Doppler markers in improving antenatal detection and surgical planning. Integrating such diagnostic techniques into routine care can markedly improve maternal and fetal outcomes in high-risk pregnancies.

To assess whether machine learning (ML) can accurately evaluate functional kinematics in people with low back pain (LBP) when judged by psychometric properties, including validity, reliability, and measurement error. A systematic search of PubMed, Scopus, Web of Science, and IEEE Xplore identified studies applying ML with kinematic inputs for LBP assessment. Risk of bias was assessed using the Newcastle-Ottawa Scale and selected COSMIN domains. Twenty studies met inclusion. Most reported criterion validity via accuracy, while few examined reliability or measurement error. Inertial sensors and support vector machines were the most common methods. ML shows strong validity for LBP movement assessment, but limited psychometric reporting constrains clinical use.

Purpose This paper aims to assess daily fluctuations in grief reactions among Vietnamese bereaved. Although grief is a universal experience, current understanding of the progression and predictive factors of bereavement-related distress predominantly originates from Western settings. Research indicates cultural variations in the development of grief over time. Notably, there has not been a study investigating how bereavement-related distress manifests in Vietnam. Design/methodology/approach Experience sampling method (ESM) can provide detailed, real-time data on daily reactions. Hundred Vietnamese bereaved adults (>18 years old) who lost a loved one in the last 6 months will complete a 2-week ESM assessment app (mPath) every 3 months for 6 months. The app sends daily reminders to complete a questionnaire about grief reactions and daily life context. Participants will complete a baseline mental health assessment before each ESM period. Findings Data collection for ESM assessments began in June 2025 and will end in December 2025. As of September 2025, 91 participants have been enrolled. A mix of longitudinal and fine-grained data will reveal daily fluctuations of grief reactions, long-term trajectories and associated contextual outcomes. Originality/value This study represents the inaugural research endeavor to digitally monitor grief trajectories among Vietnamese bereaved individuals. This study holds substantial potential to contribute to the development of more nuanced, culturally sensitive and technologically advanced bereavement support.