MétaCan
Menu
Back to cohort
Record W4415556602 · doi:10.1016/j.tfp.2025.101068

Linking forests, coasts, and people: social media insights into sentiment and wellness perceptions in China’s nature reserves

2025· article· en· W4415556602 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueTrees Forests and People · 2025
Typearticle
Languageen
FieldEnvironmental Science
TopicUrban Green Space and Health
Canadian institutionsUniversity of British Columbia
FundersNational Forestry and Grassland AdministrationHumanities and Social Science Fund of Ministry of Education of ChinaPriority Academic Program Development of Jiangsu Higher Education InstitutionsChina Scholarship Council
KeywordsVisitor patternNature reserveLatent Dirichlet allocationPerceptionSocioeconomic statusSocial mediaLivelihoodTourism

Abstract

fetched live from OpenAlex

• Forest reserves offer restorative and immersive experiences for individual psychological well-being. • Coastal reserves promote social bonding and relaxation through group activities and open environments. • Forests mainly support personal health, while coasts foster collective wellness. • Landscape structure and trail systems drive wellness in forests. • Climatic comfort and blue-green space are key for coastal wellness experiences. Nature reserves (NRs) are vital for ecological conservation and play an increasingly important role in public well-being in China. However, the social and emotional dynamics underlying visitor wellness perceptions across different reserve types remain underexplored. In this study, we analyzed a dataset of 549,682 valid comments collected from Douyin and CTrip, covering 474 National Nature Reserves (NNRs) in China between 2016 and 2024. Using natural language processing and StructBERT-based sentiment classification, we quantified the Perceived Sentiment Index (PSI) and identified wellness-related themes via Latent Dirichlet Allocation (LDA) topic modeling. We further integrated correlation analysis and SHAP-based machine learning interpretation to assess how ecological, climatic, infrastructural, and socioeconomic factors shape the Wellness Topic Score (WTS). The results revealed that forest and coastal NNRs received the highest levels of positive sentiment, with PSI values of 0.82 and 0.88, respectively. Forest reserves were most strongly associated with restorative and immersive experiences, while coastal reserves emphasized social bonding and relaxation. Spatial and temporal analysis indicated significant regional and seasonal variations in wellness perception, with forest NNRs showing peaks in spring and autumn, and coastal NNRs peaking in summer. SHAP interpretation demonstrated that wellness perception in forest reserves was primarily driven by landscape structure and trail systems, whereas in coastal reserves, climatic comfort and blue-green space ratio were dominant factors. Our findings provide robust quantitative evidence for differentiated health management in protected areas and enhance understanding of how digital narratives reflect and shape collective well-being in the context of large-scale nature–human interactions.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: Observational
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.927
Threshold uncertainty score0.997

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0010.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.007
GPT teacher head0.256
Teacher spread0.249 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it