Assessing the perception of urban parks and understanding the relationship between environmental characteristics and conflicts in park usage are crucial for the design and management of urban parks. However, quantifying perceptions of parks in large spaces poses challenges, and different regional cultures also exhibit variations in park usage. Therefore, this study aims to explore from a cross-cultural perspective how the environmental characteristics and perceptions of parks affect visitors' emotions. This research collected online comment data from Weibo check-ins in Shanghai and tweets in London between 2022 and 2023. It applied natural language processing (NLP) technology using SnowNLP for sentiment semantic keyword extraction, identifying the sentiment index of each data entry to quantify visitors' sentiments towards urban parks in Shanghai and London. Simultaneously, street view panoramas were obtained for semantic segmentation using the SegNet model and ADE20K to quantify spatial perceptions as independent variables. On this basis, we used nonlinear regression models and MGWR models to explore the relationship between visitors' sentiment values in parks and the park environment. The results showed that walkability in Shanghai was found to more easily bring positive sentiments to visitors, while visitors in London paid more attention to imageability. Walkability, accessibility, and imageability are of the same importance in Shanghai and London, but the correlation and emphasis of visitor perceptions differ, indicating potential conflicts in park usage among different user groups in the two cities' urban parks. Overall, our study offers differentiated planning suggestions that can provide information for urban design decisions, ultimately contributing to the improvement of human well-being.

中文翻译：

---

跨文化视角下公园环境特征和游客感知对游客情绪的影响


评估对城市公园的感知并了解环境特征与公园使用冲突之间的关系对于城市公园的设计和管理至关重要。然而，量化对大空间公园的感知带来了挑战，并且不同的地区文化也表现出公园使用的不同。因此，本研究旨在从跨文化的角度探讨公园的环境特征和感知如何影响游客的情绪。本研究收集了 2022 年至 2023 年间上海微博签到和伦敦推文的在线评论数据。它应用自然语言处理 （NLP） 技术，使用 SnowNLP 进行情感语义关键字提取，识别每个数据条目的情感指数，以量化游客对上海和伦敦城市公园的情感。同时，使用 SegNet 模型和 ADE20K 获得街景全景图进行语义分割，将空间感知量化为自变量。在此基础上，我们使用非线性回归模型和 MGWR 模型来探索公园内游客的情绪值与公园环境之间的关系。结果显示，上海的步行性更容易为游客带来积极的情绪，而伦敦的游客更关注可形象性。在上海和伦敦，步行性、可达性和可形象性同等重要，但游客感知的相关性和重点不同，这表明这两个城市城市公园的不同用户群体在公园使用方面存在潜在冲突。 总体而言，我们的研究提供了差异化的规划建议，可以为城市设计决策提供信息，最终有助于改善人类福祉。