How the natural environment in downtown neighborhood affects physical activity and sentiment: Using social media data and machine learning

Assessing the Impact of Urban Environments on Mental Health and Perception Using Deep Learning: A Review and Text Mining Analysis

Understanding how outdoor environments affect mental health outcomes is vital in today's fast-paced and urbanized society. Recently, advancements in data-gathering technologies and deep learning have facilitated the study of the relationship between the outdoor environment and human perception. In a systematic review, we investigate how deep learning techniques can shed light on a better understanding of the influence of outdoor environments on human perceptions and emotions, with an emphasis on mental health outcomes. We have systematically reviewed 40 articles published in SCOPUS and the Web of Science databases which were the published papers between 2016 and 2023. The study presents and utilizes a novel topic modeling method to identify coherent keywords. By extracting the top words of each research topic, and identifying the current topics, we indicate that current studies are classified into three areas. The first topic was "Urban Perception and Environmental Factors" where the studies aimed to evaluate perceptions and mental health outcomes. Within this topic, the studies were divided based on human emotions, mood, stress, and urban features impacts. The second topic was titled "Data Analysis and Urban Imagery in Modeling" which focused on refining deep learning techniques, data collection methods, and participants' variability to understand human perceptions more accurately. The last topic was named "Greenery and visual exposure in urban spaces" which focused on the impact of the amount and the exposure of green features on mental health and perceptions. Upon reviewing the papers, this study provides a guide for subsequent research to enhance the view of using deep learning techniques to understand how urban environments influence mental health. It also provides various suggestions that should be taken into account when planning outdoor spaces.

Green and blue space exposure and non-communicable disease related hospitalizations: A systematic review

The global increase in non-communicable diseases (NCDs) presents a critical public health concern. Emerging evidence suggests that exposure to natural environments may reduce the risk of developing NCDs through multiple pathways. The present systematic review aims to synthesize and evaluate the observational evidence regarding associations between exposure to green and blue spaces and hospital admissions related to NCDs. A comprehensive literature search strategy was conducted in Embase (Ovid), PubMed, and Web of Science. The risk of bias and quality of the evidence were assessed using The Navigation Guide methodology, an approach specifically designed for environmental health research. Of 3060 search results, 17 articles were included. Notably, the majority of the studies (n = 14; 82.4%) were published from 2020 onwards. Most studies were conducted in the United States (n = 6; 35.3%) and China (n = 4; 23.5%). Exposure to green spaces was assessed through all studies, while only three included blue spaces. In terms of study design, cohort design was employed in nearly half of the studies (n = 8; 47.1%), followed by case-crossover design (n = 3, 17.6%). Over 75% of the included studies (n = 13) had a high or probably high rating in the risk of bias assessment. The studies encompassed diverse NCD outcome domains; cardiovascular diseases (CVDs) (n = 10), respiratory diseases (RSDs) (n = 2), heat-related diseases (n = 1), metabolic diseases (n = 2), cancer (n = 1), neurodegenerative diseases (NDDs) (n = 2), and mental health disorders (n = 2). The present review suggests that a clear link between blue space exposure and NCD hospital admissions is not evident. However, exposure to green spaces appears to predominantly have a protective effect, although the direction of the association varies across different outcome domains. The heterogeneity among the outcome domains together with the limited number of studies, emphasizes the need for more robust evidence.

Exploring the non-linear relationship and synergistic effect between urban built environment and public sentiment integrating macro- and micro-level perspective: a case study in San Francisco

Public sentiment can effectively evaluate the public's feelings of well-being in the urban environment and reflect the quality of the spatial environment to a certain extent. Previous studies on the relationship between public sentiment and urban built environmental factors have yielded meaningful results. However, few studies have focused on the effect of micro-built environment on public sentiment at the street level, which directly shapes people's perceptions. In addition, the nonlinear relationship and synergistic effect among urban built environmental factors have been commonly disregarded in previous studies, resulting in an incomplete understanding of the impact of urban built environment on public emotions. Therefore, this paper takes San Francisco as a study case to explore the complex relationship between urban built environmental factors and public emotions. Specifically, this paper measures the polarity of public emotions through sentiment analysis on Twitter data, establishes a comprehensive built environment index system from both macro- and micro- perspectives, and subsequently explores the complex relationship between the urban built environment and public sentiment through the OLS model and Shapley Additive Explanation algorithm. Results show that: (1) micro-built environmental factors have a significant influence on public emotion, although they have been frequently ignored. (2) Public sentiment tends to be more positive in areas with recreation facilities, mixed land use, rich street view visual environment, suitable thermal and acoustic environment, balanced income, and a suitable degree of high population density. (3) A nonlinear relationship and threshold effect exist between the built environmental variables and the semantic orientations of public emotion. Environment improvement strategies based on the synergic effect between variables can effectively promote the generation of positive emotions. Our empirical findings can offer valuable insights to promote feelings of well-being and foster an urban development approach through strategic interventions within the urban built environment.

Social media insights into spatio-temporal emotional responses to COVID-19 crisis

The Coronavirus pandemic has presented multifaceted challenges in urban emotional well-being and mental health management. Our study presents a spatio-temporal sentiment mining (STSM) framework to address these challenges, focusing on the space-time geography and environmental psychology. This framework analyzes the distribution and trends of 6 categories of public sentiments in Shanghai during the COVID-19 crisis, considering the potential urban spatial influencing factors. The research specifically draws on social media data temporally coinciding with the spread of COVID-19 and the pre-trained language model RoBERTa-wwm-ext to classify public sentiment, in order to characterize the distribution and trends of dominant urban sentiment under the influence of epidemic at different phases. The interactions between urban geospatial features and sentiments are further modelled and explained using LightGBM algorithm and SHapley Additive exPlanations (SHAP) technique. The experimental findings reveal the subtle yet dynamic impact of the urban environment on the long-term spatial variation and trends of public sentiment under the epidemic, with green spaces and socio-economic status emerging as significant factors. Regions with higher permanent population consumption demonstrated more positive sentiments, underscoring the significance of socio-economic factors in urban planning and public health policy. This research offers the most extensive analysis to date on the influence of urban characteristics on public sentiment during Shanghai's epidemic life cycle also lays the groundwork for applying the STSM framework in future crises beyond COVID-19.

Association of residential greenness with chronotype among children

BACKGROUND

The association between residential greenness and chronotype remains unclear, especially among children. The current study aimed to explore the associations between residential greenness and chronotype parameters in children and examine potential pathways for these associations.

METHODS

In this cross-sectional study, 16,421 children ages 3-12 were included. Two satellite-derived vegetation indices, i.e., the normalized difference vegetation index (NDVI) and the enhanced vegetation index (EVI), were used to estimate residential greenness. The mid-sleep point on a workday (MSW) and the mid-sleep point on free days (MSF) were considered. And mid-sleep time on free days adjusted for sleep debt (MSFsc) was used as an indicator of chronotype. In addition to multivariable linear regression models, subgroup analyses were conducted to explore effect modifiers, and mediation analyses were used to explore possible mediating mechanisms of air pollutants underlying the associations.

RESULTS

An interquartile range (IQR) increase in both NDVI500-m and EVI500-m was significantly associated with an earlier MSFsc of -0.061 (95 % confidence interval (CI): -0.072, -0.049) and -0.054 (95 % CI: -0.066, -0.042), respectively. Non-linear dose response relationships were discovered between greenness indices and MSFsc and MSF. The results of stratified analyses showed the effect of residential greenness on MSW was stronger among primary school children and individuals with higher household income than among kindergarten children and those with lower household income. The joint mediation effects of PM2.5, PM1, PM10, NO2, and SO2 on the associations of NDVI500-m and EVI500-m with MSFsc were 89.6 % and 76.0 %, respectively.

CONCLUSIONS

Higher levels of residential greenness may have beneficial effects on an earlier chronotype in the child population, by reducing the effects of air pollutants, especially PM2.5. Our research hopes to promote the deployment of green infrastructure and healthy urban design strategies.