Understanding Emotional Disclosure via Diary-keeping in Quarantine on Social Media (preprint)

Quarantine is a widely-adopted measure during health crises caused by highly-contagious diseases like COVID-19, yet it poses critical challenges to public mental health. Given this context, emotional disclosure on social media in the form of keeping a diary emerges as a popular way for individuals to express emotions and record their mental health status. However, the exploration of emotional disclosure via diary-keeping on social media during quarantine is underexplored, understanding which could be beneficial to facilitate emotional connections and enlighten health intervention measures. Focusing on this particular form of self-disclosure, this work proposes a quantitative approach to figure out the prevalence and changing patterns of emotional disclosure during quarantine, and the possible factors contributing to the negative emotions. We collected 58, 796 posts with the "Quarantine Diary" keyword on Weibo, a popular social media website in China. Through text classification, we capture diverse emotion categories that characterize public emotion disclosure during quarantine, such as annoyed, anxious, boring, happy, hopeful and appreciative. Based on temporal analysis, we uncover the changing patterns of emotional disclosure from long-term perspectives and period-based perspectives (e.g., the gradual decline of all negative emotions and the upsurge of the annoyed emotion near the end of quarantine). Leveraging topic modeling, we also encapsulate the possible influencing factors of negative emotions, such as freedom restriction and solitude, and uncertainty of infection and supply. We reflect on how our findings could deepen the understanding of mental health on social media and further provide practical and design implications to mitigate mental health issues during quarantine.

Images Connect Us Together: Navigating a COVID-19 Local Outbreak in China Through Social Media Images (preprint)

Social media images, curated or casual, have become a crucial component of communicating situational information and emotions during health crises. Despite its prevalence and significance in informational dissemination and emotional connection, there lacks a comprehensive understanding of visual crisis communication in the aftermath of a pandemic which is characterized by uncertain local situations and emotional fatigue. To fill this gap, this work collected 345,423 crisis-related posts and 65,376 original images during the Xi'an COVID-19 local outbreak in China, and adopted a mixed-methods approach to understanding themes, goals, and strategies of crisis imagery. Image clustering captured the diversity of visual themes during the outbreak, such as text images embedding authoritative guidelines and ``visual diaries'' recording and sharing the quarantine life. Through text classification of the post that visuals were situated in, we found that different visual themes highly correlated with the informational and emotional goals of the post text, such as adopting text images to convey the latest policies and sharing food images to express anxiety. We further unpacked nuanced strategies of crisis image use through inductive coding, such as signifying authority and triggering empathy. We discuss the opportunities and challenges of crisis imagery and provide design implications to facilitate effective visual crisis communication.

Heart-on-a-chip model of immune-induced cardiac dysfunction reveals the involvement of free mitochondrial DNA and therapeutic effects of endothelial exosomes (preprint)

Cardiovascular disease continues to take more human lives than all cancer combined, prompting the need for improved research models and treatment options. Despite a significant progress in development of mature heart-on-a-chip models of fibrosis and cardiomyopathies starting from induced pluripotent stem cells (iPSCs), human cell-based models of myocardial inflammation are lacking. Here, we bioengineered a vascularized heart-on-a-chip system with circulating immune cells to model SARS-CoV-2-induced acute myocarditis. Briefly, we observed hallmarks of COVID-19-induced myocardial inflammation in the heart-on-a-chip model, as the presence of immune cells augmented the expression levels of proinflammatory cytokines, triggered progressive impairment of contractile function and altered intracellular calcium transient activities. An elevation of circulating cell-free mitochondrial DNA (ccf-mtDNA) was measured first in the in vitro heart-on-a-chip model and then validated in COVID-19 patients with low left ventricular ejection fraction (LVEF), demonstrating that mitochondrial damage is an important pathophysiological hallmark of inflammation induced cardiac dysfunction. Leveraging this platform in the context of SARS-CoV-2 induced myocardial inflammation, we established that administration of human umbilical vein-derived EVs effectively rescued the contractile deficit, normalized intracellular calcium handling, elevated the contraction force and reduced the ccf- mtDNA and chemokine release via TLR-NF-kB signaling axis.

Clinical Characteristics and Short-term Outcomes of Acute Pancreatitis with COVID-19 (preprint)

Introduction: The existing literature on the combination of acute pancreatitis (AP) and COVID-19 is scarce. The objective of our study is to compare the clinical outcomes and occurrence of long COVID syndrome in AP patients with and without COVID-19, while investigating the potential impact of COVID-19 on the severity, mortality rate, and long COVID syndrome in these patients.Materials and methods This retrospective, observational study was conducted at a single center. It included patients aged 18 years and above who were diagnosed with AP during the pandemic. Patients were categorized into two groups based on the results of RT-qPCR testing: the COVID-19 positive group and the COVID-19 negative group. The study aimed to compare the severity of AP, mortality rate, and occurrence of long COVID syndrome between these two groups.Result A retrospective review was conducted on 122 patients diagnosed with acute pancreatitis between December 1, 2022, and January 31, 2023. Out of these patients, 100 were included in the study. The analysis revealed no significant differences in mortality rate, severity, and sequelae between AP patients with COVID-19 and those without COVID-19 (p > 0.005). However, a statistically significant difference was observed in the occurrence of long COVID syndrome, specifically in the presence of cough (P = 0.04).Conclusion This study demonstrates that the presence of COVID-19 in patients with pancreatitis does not lead to an increase in the mortality and severity rate of pancreatitis.

Attributed Network Embedding Model for Exposing COVID-19 Spread Trajectory Archetypes (preprint)

The spread of COVID-19 revealed that transmission risk patterns are not homogenous across different cities and communities, and various heterogeneous features can influence the spread trajectories. Hence, for predictive pandemic monitoring, it is essential to explore latent heterogeneous features in cities and communities that distinguish their specific pandemic spread trajectories. To this end, this study creates a network embedding model capturing cross-county visitation networks, as well as heterogeneous features related to population activities, human mobility, socio-demographic features, disease attribute, and social interaction to uncover clusters of counties in the United States based on their pandemic spread transmission trajectories. We collected and computed location intelligence features from 2,787 counties from March 3 to June 29, 2020 (initial wave). Second, we constructed a human visitation network, which incorporated county features as node attributes, and visits between counties as network edges. Our attributed network embeddings approach integrates both typological characteristics of the cross-county visitation network, as well as heterogeneous features. We conducted clustering analysis on the attributed network embeddings to reveal four archetypes of spread risk trajectories corresponding to four clusters of counties. Subsequently, we identified four features—population density, GDP, minority status, and POI visits—as important features underlying the distinctive transmission risk patterns among the archetypes. The attributed network embedding approach and the findings identify and explain the non-homogenous pandemic risk trajectories across counties for predictive pandemic monitoring. The study also contributes to data-driven and deep learning-based approaches for pandemic analytics to complement the standard epidemiological models for policy analysis in pandemics.

Can the establishment of national sanitary cities better resist the impact of COVID-19?

The global spread of COVID-19 has led to profound reflection on building a global public health security system. This paper uses the urban data collected during the COVID-19 epidemic in China in 2020 to evaluate the effect of the National Sanitary City (NSC) policy on the prevention and control of that epidemic at different stages. We found that the NSC policy was able to curb the occurrence and transmission of the epidemic the epidemic effectively after controlling a series of factors such as urban characteristics, population mobility and pathogen transmission. Compared with non-NSCs, the NSCs were better able to control the number of infected people and the infection rate and transmission rate, and this performance was even more impressive when the epidemic gradually entered the sporadic distribution stage. The heterogeneity analysis shows that the impact of the NSC policy on the prevention and control of COVID-19 differs according to the economic development level and population size. To a certain extent, the NSC policy has blocked the spread of viruses by continuously improving the urban medical and health system and strengthening the publicity concerning infectious disease prevention and control knowledge.

Model Explainability in Physiological and Healthcare-based Neural Networks (preprint)

The estimation and monitoring of SpO2 are crucial for assessing lung function and treating chronic pulmonary diseases. The COVID-19 pandemic has highlighted the importance of early detection of changes in SpO2, particularly in asymptomatic patients with clinical deterioration. However, conventional SpO2 measurement methods rely on contact-based sensing, presenting the risk of cross-contamination and complications in patients with impaired limb perfusion. Additionally, pulse oximeters may not be available in marginalized communities and undeveloped countries. To address these limitations and provide a more comfortable and unobtrusive way to monitor SpO2, recent studies have investigated SpO2 measurement using videos. However, measuring SpO2 using cameras in a contactless way, particularly from smartphones, is challenging due to weaker physiological signals and lower optical selectivity of smartphone camera sensors. The system includes three main steps: 1) extraction of the region of interest (ROI), which includes the palm and back of the hand, from the smartphone-captured videos; 2) spatial averaging of the ROI to produce R, G, and B time series; and 3) feeding the time series into an optophysiology-inspired CNN for SpO2 estimation. Our proposed method can provide a more efficient and accurate way to monitor SpO2 using videos captured from consumer-grade smartphones, which can be especially useful in telehealth and health screening settings.

Epidemiology and pathogen profile of Kawasaki disease from a single center in China, 2018-2020

Background: It has been reported that the infections have played an important role in the pathogenesis for pediatric rheumatic diseases. The COVID-19 had the impact on the frequency of these diseases and led to a remarkable decrease of them, which confirmed the role of infections in these diseases. Objectives: To investigate the epidemiologic characteristics and pathogen profile of Kawasaki disease(KD) from a single center in China from 2018 to 2020 during the Coronavirus Disease 2019 (COVID-19) pandemic period.

Prewhitening and Normalization Help Detect a Strong Cross-Correlation Between Daily Wastewater SARS-CoV-2 RNA Abundance and COVID-19 Cases in a Community (preprint)

Wastewater surveillance is a promising technology for real-time tracking and even early detection of COVID-19 infections in communities. Although correlation analysis between wastewater surveillance data and the daily clinical COVID-19 case numbers has been frequently conducted, the importance of stationarity of the time-series data has not been well addressed. In this study, we demonstrated that strong yet spurious correlation could arise from non-stationary time-series data in wastewater surveillance, and data prewhitening to remove trends helped to reveal distinct cross-correlation patterns between daily clinical case numbers and daily wastewater SARS-CoV-2 concentration during a lockdown period in 2020 in Honolulu, Hawaii. Normalization of wastewater SARS-CoV-2 concentration by the endogenous fecal viral markers in the same samples significantly improved the cross-correlation, and the best correlation was detected at a two-day lag of the daily clinical case numbers. The detection of a significant correlation between daily wastewater SARS-CoV-2 RNA abundance and clinical case numbers also suggests that disease burden fluctuation in the community should not be excluded as a contributor to the often observed weekly cyclic patterns of clinical cases.

Effect of Traditional Chinese Medicine in patients with COVID-19: A multi-center retrospective cohort study (preprint)

Background Traditional Chinese medicine (TCM) has been applied in the treatment of COVID-19 in China, but its effectiveness and safety need evaluation.Methods A multi-center retrospective cohort study was carried out, with cumulative TCM treatment period of ≥ 3 days during hospitalization as exposure. Data came from consecutive inpatients in 4 medical centers in Wuhan, China. After data extraction, verification and cleaning, confounding factors were adjusted by inverse probability of treatment weighting, and the Cox proportional hazards regression model was used for statistical analysis.Results A total of 2272 COVID-19 patients were included, including 1684 in the TCM group and 588 in the control group. Compared with the control group, the hazard ratio for the deterioration rate in the TCM group was 0.52 [95% CI: (0.41, 0.64), P < 0.001]. The results were consistent across patients of varying severity at admission, and two sensitivity analyses confirmed the robustness of the results. In addition, the hazard ratio for all-cause mortality in the TCM group was 0.29 (95% CI = 0.19–0.44, P < 0.001). For safety, the proportion of patients with abnormal liver function or renal function in the TCM group was smaller.Conclusion This real-world study indicates that the addition of a full course of TCM therapy to basic conventional treatment, may reduce the deterioration rate and all-cause mortality of COVID-19 patients with safety. This result can provide evidence to support the current treatment of COVID-19 and new respiratory infectious diseases in the future. Additional prospective clinical trial is needed to evaluate the efficacy and safety of specific TCM interventions.Trial registration: ChiCTR, ChiCTR2200062917. Registered 23 August 2022, http://www.chictr.org.cn/showproj.aspx?proj=171556.

Individual bat viromes reveal the co-infection, spillover and emergence risk of potential zoonotic viruses (preprint)

Bats are reservoir hosts for many zoonotic viruses. Despite this, relatively little is known about the diversity and abundance of viruses within bats at the level of individual animals, and hence the frequency of virus co-infection and inter-species transmission. Using an unbiased meta-transcriptomics approach we characterised the mammalian associated viruses present in 149 individual bats sampled from Yunnan province, China. This revealed a high frequency of virus co-infection and species spillover among the animals studied, with 12 viruses shared among different bat species, which in turn facilitates virus recombination and reassortment. Of note, we identified five viral species that are likely to be pathogenic to humans or livestock, including a novel recombinant SARS-like coronavirus that is closely related to both SARS-CoV-2 and SARS-CoV, with only five amino acid differences between its receptor-binding domain sequence and that of the earliest sequences of SARS-CoV-2. Functional analysis predicts that this recombinant coronavirus can utilize the human ACE2 receptor such that it is likely to be of high zoonotic risk. Our study highlights the common occurrence of inter-species transmission and co-infection of bat viruses, as well as their implications for virus emergence.

Study on the Impact of Supply Chain Dynamic Capabilities on Long-Term Performance of Enterprises

The risk of frequent disasters is becoming a huge challenge for enterprises and their supply chains. In particular, sudden global public health events have brought a great test to the supply chain. How to make sustainable planning and preparedness and smoothly carry out supply chain operations and obtain sustainable firm performance in the complex market environment requires urgent attention from industries and academia. The different effects of supply chain operational capability and dynamic capability on the long-term performance and short-term performance of enterprises are still unclear;therefore, a model was established to discuss this. Based on the theory of dynamic capability, a relational model between supply chain dynamic capability, supply chain operational capability, and firm performance was constructed, a hypothesis testing method and Amos software were used to verify the set model, and the mechanisms of supply chain dynamic capability and supply chain operational capability on firm performance were discussed. The empirical results show that supply chain operational capability has a mediating effect on supply chain dynamic capability and firm performance, and supply chain dynamic capability has a moderating impact on supply chain operational capability and firm performance. The supply chain and its enterprises should cultivate and continuously improve the supply chain dynamic capability as soon as possible, so that in the face of emergencies, the supply chain operation capability can be reasonably configured to avoid damage, improve firm performance, and gain competitive advantages.

SARS-CoV-2 infected cells sprout actin-rich filopodia that facilitate viral invasion (preprint)

Emerging COVID-19 pandemic caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) poses a great threat to human health and economics. Although SARS-CoV-2 entry mechanism has been explored, little is known about how SARS-CoV-2 regulates the host cell remodeling to facilitate virus invasion process. Here we unveil that SARS-CoV-2 boosts and repurposes filopodia for entry to the target cells. Using SARS-CoV-2 virus-like particle (VLP), real-time live-cell imaging and simulation of active gel model, we reveal that VLP-induced Cdc42 activation leads to the formation of filopodia, which reinforce the viral entry to host cells. By single-particle tracking and sparse deconvolution algorithm, we uncover that VLP particles utilize filopodia to reach the entry site in two patterns, surfing and grabbing, which are more efficient and faster than entry via flat plasma membrane regions. Furthermore, the entry process via filopodia is dependent on the actin cytoskeleton and actin-associated proteins fascin, formin, and Arp2/3. Importantly, either inhibition the actin cross-linking protein fascin or the active level of Cdc42 could significantly hinders both the VLP and the authentic SARS-CoV-2 entry. Together, our results highlight that the spatial-temporal regulation of the actin cytoskeleton by SARS-CoV-2 infection makes filopodia as a highway for virus entry, which emerges as an antiviral target.

Current situation of construction and management of infectious diseases department and fever clinics in medical institutions in Jiangsu Province

OBJECTIVE: To analyze theconstruction of infectious diseases departments and fever clinics in medical institutions at all levels in Jiangsu Province after the COVID-19 epidemic, and to provide a basis for promoting their standardized construction. METHODS: A questionnaire survey was conducted on the construction of infectious diseases departments and fever clinics in 429 medical institutions of Jiangsu Province from July to December 2020, including the overview of medical institutions, the construction status of infectious diseases departments, the construction status and future construction plans of fever clinics, etc. RESULTS: The construction rate of infectious diseases department and fever clinics in medical institutions of Jiangsu province were 33.3% and 75.3% respectively. Ventilation by opening window for was the main form of airflow organization in infectious diseases department and fever clinics, and independent ICUs and negative pressure wards were not set up in most of infectious diseases departments. The setting rate of "three zones and two channels" in fever clinics was high(96.9%), but most of them were not equipped with special CT for fever clinics patients. The proportion of air conditioning and ventilation system without air disinfection devices in the of fever clinics of medical institutions at all levels was higher than 90%. Considering the both hardware construction and quality management, the situation in tertiary medical institutions were superior to secondary medical institutions, and secondary medical institutions were superior to primary medical institutions. Various construction indicators and management systems failed to fully meet the requirements of documents and standards. CONCLUSION: Jiangsu province actively promotes the construction of infectious diseases department and fever clinic layout, but there is still a gap with the construction standard, which is necessary to further promote standardized construction. We should mend the shortages, strengthen the weakness, expand the bases, comprehensively improve the service and anti-epidemic capacity of infectious diseases departments, fever clinics and even the entire medical and health system, so as to better serve the health and life safety of the people.

Attributed Network Embedding Model for Exposing COVID-19 Spread Trajectory Archetypes (preprint)

The spread of COVID-19 revealed that transmission risk patterns are not homogenous across different cities and communities, and various heterogeneous features can influence the spread trajectories. Hence, for predictive pandemic monitoring, it is essential to explore latent heterogeneous features in cities and communities that distinguish their specific pandemic spread trajectories. To this end, this study creates a network embedding model capturing cross-county visitation networks, as well as heterogeneous features to uncover clusters of counties in the United States based on their pandemic spread transmission trajectories. We collected and computed location intelligence features from 2,787 counties from March 3 to June 29, 2020 (initial wave). Second, we constructed a human visitation network, which incorporated county features as node attributes, and visits between counties as network edges. Our attributed network embeddings approach integrates both typological characteristics of the cross-county visitation network, as well as heterogeneous features. We conducted clustering analysis on the attributed network embeddings to reveal four archetypes of spread risk trajectories corresponding to four clusters of counties. Subsequently, we identified four features as important features underlying the distinctive transmission risk patterns among the archetypes. The attributed network embedding approach and the findings identify and explain the non-homogenous pandemic risk trajectories across counties for predictive pandemic monitoring. The study also contributes to data-driven and deep learning-based approaches for pandemic analytics to complement the standard epidemiological models for policy analysis in pandemics.

Risk Factors Associated With Increased Anxiety Sensitivity in Children and Adolescents in Northwest China During COVID-19 Pandemic Lockdown

Purpose A large body of evidence has revealed that the sudden outbreak of public health emergencies induces dramatic effects on the mental health of the general public. We aimed to investigate the level of anxiety sensitivity and its risk factors in children and adolescents from northwest China during the COVID-19 pandemic lockdown in early 2020. Methods A cross-sectional survey was conducted through the Wenjuanxing platform using a convenience sampling method between 18 and 26 February 2020. The self-designed questionnaire contained sociodemographic characteristics, factors associated with the COVID-19 pandemic, and the Childhood Anxiety Sensitivity Index (CASI) scale. The data from 1,091 valid questionnaires from students aged 9–17 years were analyzed using ANOVA, multiple linear regression, and binary logistic regression. Results The average CASI scores were 11.47 ± 6.631, and 642 students (58.9%) had prominent anxiety sensitivity. Gender, education level, family members participating in anti-COVID-19 work, getting ill and needing medical help during the lockdown, feeling afraid or having heart palpitations on hearing things associated with COVID-19, believing that COVID-19 would have adverse impacts on themselves or their family in the future, and fear of infection were identified as significant factors for elevated levels of anxiety sensitivity (p < 0.05). We established a multiple linear regression model for the anxiety sensitivity score. Risk factors found for anxiety sensitivity in children and adolescents during the COVID-19 lockdown included studying in secondary or high school, becoming ill during the pandemic, feeling afraid or experiencing rapid heartbeat or palpitations on hearing about the COVID-19 pandemic, thinking that COVID-19 would have an adverse impact on themselves or their family in the future, and fear of infection. Conclusions During the COVID-19 pandemic and home quarantine, scores measuring the prevalence of anxiety sensitivity in children and adolescents from northwest China were elevated. We should develop measures that especially target possible risk factors to intervene against and prevent anxiety sensitivity in children and adolescents in both the current and future pandemics.

Pre-Clinical Development of a Potent Neutralizing Antibody MW3321 With Extensive SARS-CoV-2 Variants Coverage

Since the outbreak of the coronavirus disease 2019 (COVID-19) pandemic, several variants of the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) have emerged and have consistently replaced the previous dominant variant. Therapeutics against variants of SARS-CoV-2 are urgently needed. Ideal SARS-CoV-2 therapeutic antibodies would have high potency in viral neutralization against several emerging variants. Neutralization antibodies targeting SARS-CoV-2 could provide immediate protection after SARS-CoV-2 infection, especially for the most vulnerable populations. In this work, we comprehensively characterize the breadth and efficacy of SARS-CoV-2 RBD-targeting fully human monoclonal antibody (mAb) MW3321. MW3321 retains full neutralization activity to all tested 12 variants that have arisen in the human population, which are assigned as VOC (Variants of Concern) and VOI (Variants of Interest) due to their impacts on public health. Escape mutation experiments using replicating SARS-CoV-2 pseudovirus show that escape mutants were not generated until passage 6 for MW3321, which is much more resistant to escape mutation compared with another clinical staged SARS-CoV-2 neutralizing mAb MW3311. MW3321 could effectively reduce viral burden in hACE2-transgenic mice challenged with either wild-type or Delta SARS-CoV-2 strains through viral neutralization and Fc-mediated effector functions. Moreover, MW3321 exhibits a typical hIgG1 pharmacokinetic and safety profile in cynomolgus monkeys. These data support the development of MW3321 as a monotherapy or cocktail against SARS-CoV-2-related diseases.

Forecasting of Automobile Sales Based on Support Vector Regression Optimized by the Grey Wolf Optimizer Algorithm

With the development of the Internet and big data, more and more consumer behavior data are used in different forecasting problems, which greatly improve the performance of prediction. As the main travel tool, the sales of automobiles will change with the variations of the market and the external environment. Accurate prediction of automobile sales can not only help the dealers adjust their marketing plans dynamically but can also help the economy and the transportation sector make policy decisions. The automobile is a product with high value and high involvement, and its purchase decision can be affected by its own attributes, economy, policy and other factors. Furthermore, the sample data have the characteristics of various sources, great complexity and large volatility. Therefore, this paper uses the Support Vector Regression (SVR) model, which has global optimization, a simple structure, and strong generalization abilities and is suitable for multi-dimensional, small sample data to predict the monthly sales of automobiles. In addition, the parameters are optimized by the Grey Wolf Optimizer (GWO) algorithm to improve the prediction accuracy. First, the grey correlation analysis method is used to analyze and determine the factors that affect automobile sales. Second, it is used to build the GWO-SVR automobile sales prediction model. Third, the experimental analysis is carried out by using the data from Suteng and Kaluola in the Chinese car segment, and the proposed model is compared with the other four commonly used methods. The results show that the GWO-SVR model has the best performance of mean absolute percentage error (MAPE) and root mean square error (RMSE). Finally, some management implications are put forward for reference.

Artificial Intelligent Technologies for the Construction Industry: How Are They Perceived and Utilized in Australia?

Artificial intelligence (AI) is a powerful technology that can be utilized throughout a construction project lifecycle. Transition to incorporate AI technologies in the construction industry has been delayed due to the lack of know-how and research. There is also a knowledge gap regarding how the public perceives AI technologies, their areas of application, prospects, and constraints in the construction industry. This study aims to explore AI technology adoption prospects and constraints in the Australian construction industry by analyzing social media data. This study adopted social media analytics, along with sentiment and content analyses of Twitter messages (n = 7906), as the methodological approach. The results revealed that: (a) robotics, internet-of-things, and machine learning are the most popular AI technologies in Australia;(b) Australian public sentiments toward AI are mostly positive, whilst some negative perceptions exist;(c) there are distinctive views on the opportunities and constraints of AI among the Australian states/territories;(d) timesaving, innovation, and digitalization are the most common AI prospects;and (e) project risk, security of data, and lack of capabilities are the most common AI constraints. This study is the first to explore AI technology adoption prospects and constraints in the Australian construction industry by analyzing social media data. The findings inform the construction industry on public perceptions and prospects and constraints of AI adoption. In addition, it advocates the search for finding the most efficient means to utilize AI technologies. The study helps public perceptions and prospects and constraints of AI adoption to be factored in construction industry technology adoption.