Scholarlink

<p>The utilization of urban parks facilitates the mitigation of the detrimental effects of modern living and the sustenance of physical and mental well-being. During the COVID-19 pandemic, the role of urban green spaces has become particularly significant, offering a vital opportunity for individuals to manage stress and engage in outdoor activities in line with social distancing guidelines. The growing significance of urban parks in this context underscores the imperative to examine the emotional responses of individuals utilizing these spaces. The objective of this study is to analyze the emotional experiences of individuals utilizing the High Line urban park, a significant urban transformation project, during the COVID-19 pandemic. Emotion classes were formulated according to Parrott’s emotion model. A sentiment analysis approach based on textual data was employed. The analysis results demonstrate that the Logistic Regression classifier achieved the highest performance with an F1-score of 0.90, a ROC-AUC score of 0.98, and a balanced accuracy of 0.89. The Support Vector Machine closely followed, attaining an F1-score of 0.89 and a ROC-AUC of 0.98, while the Random Forest classifier ranked third with an F1-score of 0.86 and a ROC-AUC of 0.97. Moreover, the Matthews Correlation Coefficient values for the Logistic Regression model were 0.91, 0.91, and 0.87 for training, cross-validation, and testing phases, respectively, indicating consistent and reliable model performance. Furthermore, the year 2020 emerged as a critical period characterized by significant emotional fluctuations. These changes are attributed to the significant impact of factors such as health concerns, social isolation, and accessibility restrictions during the pandemic on individuals’ emotional experiences.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Evaluation of High Line city park user satisfaction with machine learning: COVID-19 process year-based sentiment analysis

  • 期刊论文

  • 发表日期：

    2025年9月30日

查看全文
  • Şeyma Yiğit Uzunali,
  • Alper Uzunali

摘要

The utilization of urban parks facilitates the mitigation of the detrimental effects of modern living and the sustenance of physical and mental well-being. During the COVID-19 pandemic, the role of urban green spaces has become particularly significant, offering a vital opportunity for individuals to manage stress and engage in outdoor activities in line with social distancing guidelines. The growing significance of urban parks in this context underscores the imperative to examine the emotional responses of individuals utilizing these spaces. The objective of this study is to analyze the emotional experiences of individuals utilizing the High Line urban park, a significant urban transformation project, during the COVID-19 pandemic. Emotion classes were formulated according to Parrott’s emotion model. A sentiment analysis approach based on textual data was employed. The analysis results demonstrate that the Logistic Regression classifier achieved the highest performance with an F1-score of 0.90, a ROC-AUC score of 0.98, and a balanced accuracy of 0.89. The Support Vector Machine closely followed, attaining an F1-score of 0.89 and a ROC-AUC of 0.98, while the Random Forest classifier ranked third with an F1-score of 0.86 and a ROC-AUC of 0.97. Moreover, the Matthews Correlation Coefficient values for the Logistic Regression model were 0.91, 0.91, and 0.87 for training, cross-validation, and testing phases, respectively, indicating consistent and reliable model performance. Furthermore, the year 2020 emerged as a critical period characterized by significant emotional fluctuations. These changes are attributed to the significant impact of factors such as health concerns, social isolation, and accessibility restrictions during the pandemic on individuals’ emotional experiences.