Impact of the Built Environment on Public Sentiment During Winter in Cold-Region Cities: A Case Study of Harbin Based on Social Media
Open Access
Abstract
While the influence of the urban built environment on public emotions has garnered extensive attention, existing studies predominantly focus on temperate climates or warmer seasons. As a result, they rarely extend their scope to winter-specific emotions in cold-region cities, thereby overlooking the complex human–environment emotional interactions under extreme climates. To bridge this seasonal research gap, this study develops an innovative analytical framework integrating Large Language Models (LLMs) with Multiscale Geographically Weighted Regression (MGWR). Drawing on social media data, this framework leverages the powerful zero-shot reasoning capabilities of LLMs to precisely quantify the two-dimensional emotional characteristics of Valence and Arousal. Concurrently, by incorporating the multi-scale spatial modeling strengths of MGWR, it thoroughly investigates the spatial patterns and driving mechanisms of public emotions within the winter context of typical cold-region cities. The results indicate that, first, extreme climates do not lead to urban emotional suppression; instead, frozen rivers transform into vibrant emotional corridors, with the public demonstrating a high degree of thermal-psychological adaptability. Second, by incorporating winter-specific environmental variables, the research reveals a cold-region paradox of emotional valence. Specifically, under snow cover, lower winter Land Surface Temperature (LST) and winter Normalized Difference Vegetation Index (NDVI) paradoxically evoke positive emotions by reconstructing the aesthetic experience of ice-snow landscapes. Furthermore, the impact of urban service facilities on emotional arousal exhibits a significant pattern of diminishing marginal utility. Overall, the LLMs-MGWR framework achieves a closed loop of high-throughput, multi-dimensional semantic decoding and multi-scale spatial interpretation, demonstrating exceptional cross-regional generalizability. Ultimately, this study not only provides a novel paradigm for understanding human–environment interactions in complex environments but also offers transferable planning guidelines for microclimate design, facility decentralization, and the reshaping of winter blue-green infrastructure in global cold-region cities.Keywords
Funding Information
- National Natural Science Foundation of China (32201339)
This publication has 92 references indexed in Scilit:
- Winter is coming: Deciphering the longitudinal associations between everyday emotion regulation and depressive symptoms across the seasonsCurrent Psychology, 2024
- Urban landscape and climate affect residents’ sentiments based on big dataApplied Geography, 2023
- Measuring urban sentiments from social media data: a dual-polarity metric approachJournal of Geographical Systems, 2022
- Deep learning for sentiment analysis: A surveyWIREs Data Mining and Knowledge Discovery, 2018
- Effect of climate and seasonality on depressed mood among twitter usersApplied Geography, 2015
- Citizens as sensors: the world of volunteered geographyGeoJournal, 2007
- Human cold exposure, adaptation, and performance in high latitude environmentsAmerican Journal of Human Biology, 2007
- Sustainable winter cities: Future directions for planning, policy and designAtmospheric Environment, 1996
- Human health and social factors in winter climatesEnergy and Buildings, 1991
- Human adaptation to levels of environmental stimulationHuman Ecology, 1974