Fine-grained assessment of greenspace satisfaction at regional scale using content analysis of social media and machine learning

Emerging trends and knowledge domain of research on urban green open spaces and wellbeing: A scientometric review

Green Open Spaces (GOS) and its linkages to human health and wellbeing have received growing attention in the field of urban planning. In spite of increase in number of studies in this field, there is lack of scientometric perspective pertaining to this research domain. The purpose of the study is to map the research status and key research directions in the interdisciplinary domain: Green open spaces, public health and urban planning, using Citespace. Scientometric analysis (co-author, co-citation, co-word and cluster analysis) is conducted for 451 peer reviewed publications, primarily published in last two decades (2000-2021) in the web of science database. The study assessed influential authors, journals and documents to identify the intellectual structure and network of co-authorship and countries to understand research collaborations of this domain. As a result of this review, five emerging research trends in this domain are identified - Emerging data sources, Study areas at various spatial scales, Type of study, Assessment of urban GOS benefits and Urban planning contribution in the research area. In addition, critical review of these trends is conducted to understand corresponding challenges and opportunities. The critical analysis highlighted the need of generating evidence base appropriate for assessing GOS use and user perception, especially in developing nations capturing socio-demographic diversity. The use of Citespace for scientometric analysis facilitated the systematic understanding of this research area by visualizing and analyzing various patterns and trends. This study provides an intensive understanding of present research status and emerging trends of this research domain. Findings in this study are envisioned to provide practitioners, decision makers and researchers with promising future research directions.

Predicting life satisfaction based on the emotion words in self-statement texts

Measuring people's life satisfaction in real time on a large scale is quite valuable for monitoring and promoting public mental health; however, the traditional questionnaire method cannot fully meet this need. This study utilized the emotion words in self-statement texts to train machine learning predictive models to identify an individual's life satisfaction. The SVR model was found to have the best performance, with the correlation between predicted scores and self-reported questionnaire scores achieving 0.42 and the split-half reliability achieving 0.939. This result demonstrates the possibility of identifying life satisfaction through emotional expressions and provides a method to measure the public's life satisfaction online. The word categories selected through the modeling process were happy (PA), sorrow (NB), boredom (NE), reproach (NN), glad (MH), aversion (ME), and N (negation + positive), which reveal the specific emotions in self-expression relevant to life satisfaction.

Effects of the spatial patterns of urban parks on public satisfaction: evidence from Shanghai, China

CONTEXT

Urban parks need to meet the growing demand for activities vital to residents' well-being and urban development. A holistic understanding of public satisfaction with urban parks is a prerequisite for improving management.

OBJECTIVE

The spatial patterns and composition of urban parks vary greatly, and the objective of this study is to comprehensively investigate public satisfaction with urban parks and the impact of their structure.

METHODS

With the metropolis of Shanghai, China, as an example, we employed 111,814 social media data sets for 50 urban park sites to quantify public satisfaction via the long short-term memory model. We analyzed the internal, boundary and external dimensions of spatial patterns and described the internal landscape patterns from the perspectives of size, heterogeneity, aggregation, shape, diversity and landscape elements. Moreover, we used all-subset regression and hierarchical partitioning to quantify the relationship and mechanism of action between spatial patterns and public satisfaction.

RESULTS

The results indicate that the mean value of public satisfaction with urban parks was 0.716 (ranging from 0 to 1), which is generally positive or neutral. Satisfaction was influenced by the internal, boundary, and external spatial patterns of urban parks. The independent contribution rates of external transportation facility density (51.49%) and internal edge density (48.51%) to satisfaction.

CONCLUSIONS

We highlight the roles of spatial patterns, especially the degree of external transportation convenience and the edge density of urban parks at the landscape level. The findings provide guidance and recommendations for the planning and design of public satisfaction-oriented urban parks.

SUPPLEMENTARY INFORMATION

The online version contains supplementary material available at 10.1007/s10980-023-01615-z.

A systematic review of urban green space research over the last 30 years: A bibliometric analysis

Worldwide, due to rapid urbanization, the provision of urban green spaces (UGSs) has become a primary goal of urban planning. As such, research on the benefits, effects, and challenges of UGSs has gained widespread attention among scholars. This paper comprehensively analyzes three decades of UGS research and its evolution; it conducts a bibliometric analysis of approximately 4000 articles and reviews from the Web of Science platform to discover the patterns and trends characterizing UGS research over time. We found that the pioneers of initial UGS research were the United States and Canada, whereas recently the European Union and China have become the global engines of research in the field. UGS research initially focused on studying urban forests, gradually shifting toward green spaces located in inner urban areas. Early on, researchers investigated UGSs (i.e., urban forests) from an ecological perspective. However, the most current research phase focuses on the social aspects of UGSs, characterized by such keywords as environmental justice and accessibility. Furthermore, the introduction of geographic information systems (GIS) has given new impetus to the evolution of UGS research and has remained the most used technological advancement besides remote sensing techniques. As the social aspects of UGS research have gained importance, new research methods have been employed, such as machine learning, big data and social media data analysis, and artificial intelligence, most recently.

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

BACKGROUND

Natural environment might encourage physical exercise, hence enhancing human health and wellbeing. Social media offers an extensive repository of spatiotemporal data, containing details on the feelings and behaviors of individuals. However, investigations on physical activity and public sentiment in the natural environment of the downtown neighborhood are lacking in the existing literature.

METHODS

To extract environmental and behavioral information from social media data and other multi-source data, natural language processing, semantic segmentation, instance segmentation, and fully convolutional neural networks are employed. The research examines how neighborhood blue-green spaces and other health-promoting facilities affect physical activity and public sentiment.

RESULTS

The results reveal that blue space visibility, activity facilities, street furniture, and safety all have a favorable influence on physical activity with a social gradient. Amenities, perceived street safety and beauty positively correlated to public sentiment. The findings from social media about the environment and physical activity are consistent with traditional surveys from the same time period with a 0.588 kappa value.

CONCLUSION

According to our findings, social media data might be utilized to learn more about how urban environments influence people's physical activity patterns. Also, the health-promoting effects of blue space require more investigation.

Understanding different cultural ecosystem services: An exploration of rural landscape preferences based on geographic and social media data

Rural landscapes offer a variety of cultural ecosystem services (CESs). However, the relationship between rural landscape characteristics and different CESs is still poorly understood. Therefore, this study explored the rural areas of Huzhou city, China, as a case study to assess the main rural landscape characteristics of different CESs based on public preferences. First, 148 scenic spots were classified into four CESs (physical, experiential, intellectual and inspirational), and the public preferences for each scenic spot were determined by combining tourists' scores obtained from social media and government assessment scores. Then, the landscape characteristic indicators were constructed from the natural, infrastructural and sensory perspectives by combining geographic and social media data. Finally, the random forest model was used to evaluate the public preferences for rural landscape characteristics overall and for different CESs. The word frequency analysis showed that, in addition to the nature landscape, infrastructure and service had a strong influence on public preferences. The relationship with rural landscape characteristics varied across different CESs. For physical CESs, the convenience of infrastructure played a greater role than natural landscape characteristics. Experiential CESs, on the other hand, were affected by natural landscape characteristics themselves. Intellectual CESs had higher requirements for both infrastructure and nature. Inspirational CESs included sensory evaluation indicators, in addition to their focus on natural landscape characteristics and infrastructure, indicating that this category of CESs was more concerned with inner experience. The use of social media data has enriched the dimensions of sensory elements and provided new ideas and information supplements for comprehensively understanding different CESs, thus better supporting the management, planning and protection of rural landscapes.

A Literature Review of Big Data-Based Urban Park Research in Visitor Dimension

Urban parks provide multiple benefits to human well-being and human health. Big data provide new and powerful ways to study visitors’ feelings, activities in urban parks, and the effect they themselves have on urban parks. However, the term “big data” has been defined variably, and its applications on urban parks have so far been sporadic in research. Therefore, a comprehensive review of big data-based urban park research is much needed. The review aimed to summarize the big data-based urban park research in visitor dimension by a systematic review approach in combination with bibliometric and thematic analyses. The results showed that the number of publications of related articles has been increasing exponentially in recent years. Users’ days data is used most frequently in the big data-based urban park research, and the major analytical methods are of four types: sentiment analysis, statistical analysis, and spatial analysis. The major research topics of big data-based urban park research in visitor dimension include visitors’ behavior, visitors’ perception and visitors’ effect. Big data benefits urban park research by providing low-cost, timely information, a people-oriented perspective, and fine-grained site information. However, its accuracy is insufficient because of coordinate, keyword classification and different kinds of users. To move forward, future research should integrate multiple big data sources, expand the application, such as public health and human–nature interactions, and pay more attention to the big data use for overcoming pandemic. This review can help to understand the current situation of big data-based urban park research, and provide a reference for the studies of this topic in the future.

Greening the city: Thriving for biodiversity and sustainability

Urban population and urbanisation are increasing rapidly, mainly in developing countries, usually at the expense of green and blue areas. This trend will decrease the ecosystems' capacity to supply ecosystem services (ES) and threaten human wellbeing. Therefore, it is key to establish greening policies in urbanising areas, which are essential to improve the liveability of cities. Restoring and developing green and blue infrastructures using nature-based solutions is vital to improving urban biodiversity and urban ecosystems. Healthy urban ecosystems have a high capacity to supply regulating (e.g., air, noise, climate and water regulation), provisioning (e.g., food, medicinal plants, biomass) and cultural (e.g., recreation, landscape aesthetics, social cohesion) ES. This multifunctionality can provide diverse environmental, social and economic benefits to urban residents, hence contributing to the sustainability of urban areas. However, urban green and blue areas are also associated with ecosystem disservices (e.g., plant allergies or poisoning, emission of biogenic volatile organic compounds, unpleasant smells), tradeoffs (e.g., increased water consumption, wildfire risk, associated management costs) and implementation barriers (e.g., political motivation, lack of knowledge, time and workload). Overall, the SI published 8 articles from different parts of the world, such as China, the USA, Italy or Spain, focused on important aspects of greening the city (e.g., green roofs, green walls, green infrastructures, sustainable mobility).