基于大语言模型的城市街区情感空间识别与更新 策略研究——以上海市四川北路街区为例
Research on Emotional Space Identification and Regeneration Strategies for Urban Neighborhoods Based on Large Language Models: A Case Study of the North Sichuan Road Neighborhood in Shanghai
周 静
上海大学上海美术学院建筑系 副教授，博士
邝远霄
上海脉策数据科技有限公司 工程师，硕士
吴书驰（通信作者）
天津市城市规划设计研究总院有限公司 正高级建筑师，硕士，kratos83@126.com
张华钰
上海大学上海美术学院建筑系 硕士研究生
韦家璇
上海大学上海美术学院建筑系
摘要: 针对城市更新中人文情感要素量化评估难题，构建“数据采集—情感识别—更新策略”研究框架，探索人工智能技术 驱动的人本主义更新路径。研究运用大语言模型和知识图谱技术，系统整合社交媒体、市民热线、新闻副刊和深度访谈 等海量异构数据，以上海市四川北路街区为例，开展情感空间识别与更新策略研究。研究识别出8类细分情感空间，并对 3 697个空间地点数据进行情感评分。研究发现：（1）情感热点空间与物质载体高度耦合；（2）怀旧、喜悦共同构成四川 北路街区情感基底；（3）负面情感空间呈现“功能失配—节点聚集”分异规律。研究表明，多源数据与AI技术的协同应 用能够拓展情感空间解析的观测维度，为精细化城市更新中技术工具与人文价值融合提供一种可行性思路。
Abstract: Addressing the challenge of quantifying human emotional elements in urban renewal, this study constructs a research framework of "data collection – emotion recognition – urban renewal strategy" to explore human-centric renewal pathways driven by artificial intelligence technologies. By integrating large language models (LLMs) and knowledge graph technology, the research systematically synthesizes massive heterogeneous data from social media, resident hotlines, news supplement, and in-depth interviews. Taking Shanghai's North Sichuan Road neighborhood as a case study, it identifies eight categories of emotional spaces and conducts emotional scoring for 3 697 spatial data points. Key findings include: (1) There is a strong coupling relationship between emotional hotspots and physical urban fabric; (2) Nostalgia and joy collectively form the neighborhood's emotional foundation; (3) Negative emotional spaces exhibit functional mismatch-driven nodal clustering patterns. The study demonstrates that the synergistic application of multi-source data and AI technologies expands observational dimensions for emotional space analysis, providing a feasible approach to integrate technical tools with humanistic values in precision-oriented urban renewal.
关键词：多源数据；大语言模型；情感空间；城市更新；规划技术
Keyword: multi-source data; large language models; emotional space; urban regeneration; planning technologies
中图分类号：TU984
文献标识码: A
阎树鑫，万智英，李嘉男. 城市更新行动：内涵、
逻辑和体系框架[J]. 城市规划学刊，2023（1）：
62-68.
YAN Shuxin, WAN Zhiying, LI Jia'nan. Urban renewal action: connotation, logic and systemic
framework[J]. Urban Planning Forum, 2023(1): 62-68.
周静，肖阳. 人工智能时代技术进步与城乡发展
研究的新议题[J]. 上海城市规划，2022（5）：1-6.
ZHOU Jing, XIAO Yang. The issues of techno-
logical progress and urban and rural development
in the age of artificial intelligence[J]. Shanghai Urban Planning Review, 2022(5): 1-6.
唐燕. 城市更新制度与北京探索：主体—资金—
空间—运维[M]. 北京：中国城市出版社，2023.
TANG Yan. Urban renewal system and Beijing's exploration: subjects-funding-space-operations & maintenance[M]. Beijing: China City Press, 2023.
MEHRABIAN A, RUSSELL J A. An approach to
environmental psychology[M]. Cambridge, MA: The MIT Press, 1974.
RUSSELL J. A circumplex model of affect[J]. Journal of Personality and Social Psychology, 1980, 39: 1161-1178.
段义孚. 恋地情结：环境感知，态度和价值观研
究[M]. 张志丞，刘苏，译. 北京：商务印书馆，
2019.
DUAN Yifu. Topophilia: a study of environmental
perception, attitudes, and values[M]. ZHANG
Zhicheng, LIU Su, translate. Beijing: The Com-
mercial Press, 2019.
刘思达. 社会空间：从齐美尔到戈夫曼[J]. 社会
学研究，2023（4）：142-159.
LIU Sida. Social spaces: from Georg Simmel to Erving Goffman[J]. Sociological Studies, 2023(4):
142-159.
NOLD C. Emotional cartography: technologies of
the self[M]. London: Space Studios, 2009.
CAQUARD S, CARTWRIGHT W. Narrative cartography: from mapping stories to the narrative of maps and mapping[J]. The Cartographic Journal,
2014, 51(2): 101-106.
郭义超，樊红. 基于中文文本分析的微博情感地
图的制作[J]. 计算机系统应用，2017，26（2）：
25-29.
GUO Yichao, FAN Hong. Approach to make mood maps based on sentiment analysis of Chinese Micro-Blog[J]. Computer Systems & Applications, 2017, 26(2): 25-29.
ASHKEZARI-TOUSSI S, KAMEL M, SADOGHI-YAZDI H. Emotional maps based on social networks data to analyze cities emotional
structure and measure their emotional similarity[J].
Cities, 2019(86): 113-124.
PÁNEK J. Mapping citizens' emotions: partici-
patory planning support system in Olomouc, Czech
Republic[J]. Journal of Maps, 2019, 15(1): 8-12.
HE J, ZHANG J, YAO Y, et al. Extracting human
perceptions from street view images for better
assessing urban renewal potential[J]. Cities,
2023(134): 104189.
蒋源，于儒海，曹塽，等. 基于网络社交数据的城
市情绪地图及空间优化探索——以成都市为例
[J]. 规划师，2023，39（9）：56-62.
JIANG Yuan, YU Ruhai, CAO Shuang, et al. A study on urban emotional map and spatial improvement based on social networking data:
take Chengdu City as an example[J]. Planners,
2023, 39(9): 56-62.
崔璐明，曲凌雁，何丹. 基于深度学习的城市热
点空间情绪感知评价——以上海市为例[J]. 人
文地理，2021，36（5）：121-130.
CUI Luming, QU Lingyan, HE Dan. Evaluating emotional perception of spatial hotspots via deep learning: a case study of Shanghai[J]. Human Geography, 2021, 36(5): 121-130.
单卓然，安月辉，袁满，等. 基于微博大数据的城
市居民情绪时空分布特征及影响因素研究——
以武汉市主城区为例[J]. 城市发展研究，2022，
29（8）：69-76.
SHAN Zhuoran, AN Yuehui, YUAN Man, et al. Study on spatial and temporal distribution characteristics and influencing factors of urban residents' sentiment based on Weibo data: a case study of the main urban area of Wuhan[J]. Urban Development Studies, 2022, 29(8): 69-76.
周静，邝远霄，刘勇，等. 基于大语言模型的城市
街区“人—地”情感关联测度及启示——以上
海多伦路街区为例[J]. 上海城市规划，2024（3）：
102-108.
ZHOU Jing, KUANG Yuanxiao, LIU Yong, et al. Measurement and implications of 'people-place' emotional association in urban blocks based on large language models: a case study of Duolun Road Block in Shanghai[J]. Shanghai Urban
Planning Review, 2024(3): 102-108.
NADEEM M, SOHAIL S S, JAVED L, et al. Vision-enabled large language and deep learning models for image-based emotion recognition[J]. Cognitive Computation, 2024(16): 2566-2579.
仲玥，刘雨轩，叶宇. 基于大语言模型和社交媒
体数据的城市公园公众活动丰富度测度——以
上海为例[J]. 风景园林，2024，31（9）：34-41.
ZHONG Yue, LIU Yuxuan, YE Yu. Measurement of the public activity richness of urban park based
on large language models and social media data: a
case study of Shanghai[J]. Landscape Architecture, 2024, 31(9): 34-41.
ZHANG Y, YANG X, XU X, et al. Affective computing in the era of large language models: a survey from the NLP perspective[J]. arXiv, 2024: 2408.04638.
杨滔，白雪，刘扬. 城市更新中空间流的记忆重
塑——以上海四川北路城市更新为例[J]. 建筑
学报，2016（7）：17-21.
YANG Tao, BAI Xue, LIU Yang. Rebuilding the memory of spatial flows in urban renewal: a case study of Sichuan Road North in Shanghai[J]. Architectural Journal, 2016(7): 17-21.
彭晖. 购物中心对地方社会网络的影响——以
上海四川北路为例[J]. 国际城市规划，2012，
27（2）：67-72.
PENG Hui. The impact of shopping mall on local social network: a case study of North Sichuan Road
of Shanghai[J]. Urban Planning International, 2012,
27(2): 67-72.
孙施文，董轶群. 偏离与错置——上海多伦路文
化休闲步行街的规划评论[J]. 城市规划，2008
（12）：68-78.
SUN Shiwen, DONG Yiqun. Displaced and misplaced: planning evaluation of Duolun pedes-
trian street in Shanghai City[J]. City Planning Review, 2008(12): 68-78.
WANG S, SUN X, LI X, et al. GPT-NER: named
entity recognition via large language models[J]. arXiv, 2023: 2304.10428.
EKMAN P. Universal and cultural differences in facial expression of emotions[M]//COLE J.
Nebraska Symposium on Motivation. Lincoln: University of Nebraska Press, 1972: 207-283.
PLUTCHIK R. Emotion: a psychoevolutionary synthesis[M]. New York, NY: Harper & Row, 1980.
