ORIGINAL RESEARCH article
Front. Psychol.
Sec. Environmental Psychology
How Do Cultural Ecosystem Services Affect Visitor Emotions? Evidence from Social Media Data in Shanghai Urban Parks
Provisionally accepted- 1University of Edinburgh, Edinburgh, United Kingdom
- 2The University of Edinburgh School of Architecture and Landscape Architecture, Edinburgh, United Kingdom
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Traditional Cultural Ecosystem Services (CES) CES assessments rely heavily on questionnaires or interviews, which struggle to capture large-scale user perceptions and lack classification frameworks tailored to Chinese contexts. Drawing on large volumes of social media texts from five representative urban parks in Shanghai, this study proposes an integrated quantitative framework—LDA topic modeling–CES classification system–sentiment analysis–linear mixed-effects modeling (LMM)—to identify visitors' perceived CES features and evaluate their influence on emotional experiences. First, the LDA model was used to extract five CES categories, and an expert-annotated system adapted to the Chinese linguistic and cultural context was developed. The results show that Recreation and Family Engagement and Symbolic and Inspirational Landscapes are the most frequently perceived CES, whereas Education and Cognitive Engagement is least prominent. Sentiment analysis indicates that visitors' emotions are highly positive overall (with "Very Positive" exceeding 83%) and exhibit a seasonal pattern characterized by higher positivity in spring and autumn and lower levels in winter and summer. The LMM results further reveal significant differences in how various CES types affect emotional responses. Recreation and Family Engagement and Symbolic and Inspirational Landscapes significantly enhance positive emotions, while Education and Cognitive Engagement shows a weak negative association in some cases—reflecting characteristics of textual expression rather than the actual effects of educational activities. Overall, this study provides a methodological pathway for large-scale CES quantification and demonstrates the potential of social media text analysis in uncovering cultural experiences and emotional responses in urban parks. The findings offer scientific insights for park planning, experience optimization, and the design of emotionally supportive urban public spaces.
Keywords: Cultural ecosystem services, LDA Topic Modeling, sentiment analysis, social media reviews, Urban parks
Received: 24 Sep 2025; Accepted: 28 Nov 2025.
Copyright: © 2025 Shu. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Hanhan Shu
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.