Evaluating ESG Impacts in African Cities through Topic-Level Sentiment Analysis DOI
Abdou Mohamed Naira, Imade Benelallam

Published: Oct. 26, 2023

In this paper, we focus on describing the measurement of Environmental, Social, and Governance (ESG) impacts in African cities urban areas. We use Topic-Based Sentiment Analysis methodologies applied to a variety social media collected dataset. Our solution aims understand population's perception ESG cities, given their potential influence societies, leading people express thoughts through communication channels. The originality our work lies providing systematic mapping any data with issues. It also ensures comprehensive insights into subject matter.The encompasses pipeline starting collection modules, followed by enrichment based an framework. This facilitates semi-supervised topic-modeling using BERTopic domain-based keyword filtering. For Analysis, present fine-grained methodology calculating sentiment at topic level. Finally, propose diverse Key Performance Indicators (KPIs) for understanding evaluating proposed solution.

Language: Английский

Assessing and interpreting perceived park accessibility, usability and attractiveness through texts and images from social media DOI
Xukai Zhao, Yuxing Lu, Wenwen Huang

et al.

Sustainable Cities and Society, Journal Year: 2024, Volume and Issue: 112, P. 105619 - 105619

Published: July 3, 2024

Language: Английский

Citations

9
Deciphering urban bike-sharing patterns: An in-depth analysis of natural environment and visual quality in New York's Citi bike system DOI Creative Commons
Wenjing Gong, Jin Rui, Tianyu Li

et al.

Journal of Transport Geography, Journal Year: 2024, Volume and Issue: 115, P. 103799 - 103799

Published: Jan. 21, 2024

Bike-sharing offers a convenient and sustainable mode of transportation. Numerous studies have investigated the influence temporal variations in natural environment on cycling, as well impact physical street characteristics like networks infrastructures. However, few integrated compared effects visual quality cycling spatial dimension. As case study, we focused these two factors Citi Bike system weekdays weekends New York City, while accounting for sociodemographic functional factors. This study employed machine learning multiscale geographically weighted regression models at both station neighborhood scales comprehensive analysis their relationships. The results reveal that factors, particularly visibility, are more important associated with bike-sharing use. Among motorized traffic has negative weekday weekend cycling. When considering geographical location, sky openness exhibits an unfavorable specific areas. By combining our promotes optimal resource allocation development bike-friendly cities.

Language: Английский

Citations

8
Measuring human perception of residential built environment through street view image and deep learning DOI Creative Commons
Yumeng Meng, Dong Sun, Mei Lyu

et al.

Environmental Research Communications, Journal Year: 2024, Volume and Issue: 6(5), P. 055020 - 055020

Published: May 1, 2024

Abstract As an important part of the urban built environment, streets exploring influence mechanism between environment and human perception. It is one issues in building healthy cities. In this study, residential Zhongshan Distict, Dalian were selected as study site, including Mountain Low-rise Neighborhood, Old Mid-rise Modern High-rise Neighborhood. Meanwhile, spatial measurement perception evaluation street based on Deep learning view image (SVI). The used perceptions dependent variables, physical features independent variables. Finally, two regression models positive negative established to analyze relationship them. results showed that three types neighborhood, was mainly focused Neighborhood; Negative Greenness, Openness, Natural Landscape, artificial ratio horizontal interface, vertical interface had a Pedestrian occurrence rate, Enclosure, Vehicle Occurrence rate emotive. Greenness feature most affected This provided method for objectively evaluating quality environment. promoting public mental health.

Language: Английский

Citations

4
Exploring tourists' perceptions of ecosystem services in national parks to guide the optimization of management DOI
Xiaomin Xiao,

Yichen Yan,

Yuxin Qi

et al.

Journal of Cleaner Production, Journal Year: 2025, Volume and Issue: unknown, P. 145134 - 145134

Published: Feb. 1, 2025

Language: Английский

Citations

0
How to Quantify Multidimensional Perception of Urban Parks? Integrating Deep Learning-Based Social Media Data Analysis with Questionnaire Survey Methods DOI
Wenwen Huang, Xukai Zhao, Guangsi Lin

et al.

Urban forestry & urban greening, Journal Year: 2025, Volume and Issue: unknown, P. 128754 - 128754

Published: March 1, 2025

Language: Английский

Citations

0
Research on Park Perception and Understanding Methods Based on Multimodal Text–Image Data and Bidirectional Attention Mechanism DOI Creative Commons
Kai Chen, Xiuhong Lin, Tao Xia

et al.

Buildings, Journal Year: 2025, Volume and Issue: 15(9), P. 1552 - 1552

Published: May 4, 2025

Parks are an important component of urban ecosystems, yet traditional research often relies on single-modal data, such as text or images alone, making it difficult to comprehensively and accurately capture the complex emotional experiences visitors their relationships with environment. This study proposes a park perception understanding model based multimodal text–image data bidirectional attention mechanism. By integrating image incorporates encoder representations from transformers (BERT)-based feature extraction module, Swin Transformer-based cross-attention fusion enabling more precise assessment visitors’ in parks. Experimental results show that compared methods residual network (ResNet), recurrent neural (RNN), long short-term memory (LSTM), proposed achieves significant advantages across multiple evaluation metrics, including mean squared error (MSE), absolute (MAE), root (RMSE), coefficient determination (R2). Furthermore, using SHapley Additive exPlanations (SHAP) method, this identified key factors influencing experiences, “water”, “green”, “sky”, providing scientific basis for management optimization.

Language: Английский

Citations

0
Spatial heterogeneities of residents' sentiments and their associations with urban functional areas during heat waves– a case study in Beijing DOI Creative Commons

Yanrong Zhu,

Juan Wang,

Yu-Ting Yuan

et al.

Computational Urban Science, Journal Year: 2024, Volume and Issue: 4(1)

Published: March 11, 2024

Abstract The intensification of global heat wave events is seriously affecting residents' emotional health. Based on social media big data, our research explored the spatial pattern sentiments during waves (SDHW). Besides, their association with urban functional areas (UFAs) was analyzed using Apriori algorithm rule mining. It found that SDHW in Beijing were characterized by obvious clustering, hot spots predominately dispersed and far suburbs, cold mainly clustered near suburbs. As for associations function areas, green space park had significant effects positive sentiment study area, while a higher percentage industrial greater impact negative SDHW. When it comes to combined UFAs, results revealed area other more closely related SDHW, indicating significance promoting sentiment. Subdistricts lower residential traffic may have There two main UFAs impacts SDHW: combination public areas. This contributes understanding improving community planning governance when increase, building healthy cities, enhancing emergency management.

Language: Английский

Citations

2
The influence of two and three-dimensional spatial characteristics of industrial parks on the emotional well-being of employees: A case study of Shenzhen DOI
Xiao Ding, Botao Feng,

Jiahua Wu

et al.

Applied Geography, Journal Year: 2024, Volume and Issue: 171, P. 103367 - 103367

Published: Aug. 17, 2024

Language: Английский

Citations

1
Spatial and temporal dynamics of urban heat environment at the township scale: A case study in Jinan city, China DOI Creative Commons
Dongchao Wang,

Jianfei Cao,

Baolei Zhang

et al.

PLoS ONE, Journal Year: 2024, Volume and Issue: 19(9), P. e0307711 - e0307711

Published: Sept. 16, 2024

The prolonged dependence on industrial development has accentuated the cumulative effects of pollutants. Simultaneously, influenced by land construction activities and green space depletion, Urban Heat Island (UHI) effect in cities intensified year year, jeopardizing foundation sustainable urban development. Prudent spatial planning holds potential to robustly ameliorate persistent deterioration UHI phenomenon. This study selects Jinan City as a case employs autocorrelation regression algorithms explore spatiotemporal evolution urban-rural patterns at township scale. aim is identify key factors driving differentiation Land Surface Temperature (LST) from 2013 2022. research reveals trend initially rising subsequently falling LST various townships, with low-temperature concentration areas southern mountainous region northern plain area. "West-Central-East" main axis southeast Laiwu District exhibit high-temperature zones. Significant influences are attributed pollution levels, topographical factors, urbanization greenness. global Moran's Index for exceeds 0.7, indicating strong positive correlation. Cluster analysis results indicate High-High (HH) clustering central Shizhong Low-Low (LL) Shanghe County. Multiscale Geographically Weighted Regression (MGWR) outperforms (GWR) Ordinary Linear (OLR), providing more accurate reflection relationships between variables. By investigating its scale, this contributes insights future

Language: Английский

Citations

1
Exploring Combinations of Landscape Features in Urban Green Spaces and Their Recovery Effects on Minor Depression DOI
X. Li, Bo-Wei Zhu, Lei Xiong

et al.

Journal of Urban Planning and Development, Journal Year: 2024, Volume and Issue: 151(1)

Published: Nov. 26, 2024

Language: Английский

Citations

1