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

doi:10.13959/j.issn.1003-2398.2021.05.015

摘要
图/表
参考文献(0)
相关文章 (1)

全文: PDF (57056 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要基于新浪微博数据，借助深度学习方法分析上海市情绪空间分布特征，期望构建一套基于社交媒体签到数据的深度学习空间情绪感知评价方法。研究发现：①上海市热门签到地点集中分布在城市中心、交通枢纽、地铁沿线等区域。②积极情绪占比随着到市中心距离的增加呈下降趋势；人们的情绪与活动空间类型高度相关。③高等院校场所与负面情绪相关的物质空间要素多与建筑相关，办公场所的空间使用者最关注通勤问题，交通枢纽空间的管理流程和服务水平诱发了较多负面情绪。研究发现对于城市公共安全、公共卫生和设计管理的决策者有着重要启示。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	崔璐明
	曲凌雁
	何丹

关键词 ：深度学习, BERT模型, 签到 POI地图, 情绪地图, 感知评价

Abstract：The study on spatial emotional perception which arises from the intersection between Spatial Psychology and Geography is an important field of Human Geography. But its development has long been limited by data access and methods. Deep learning can provide the strong support for the quantitative analysis of spatial emotional perception. This paper attempts to build a deep learning framework which based on social media sign-in data to evaluate and analyze spatial emotional perception. In this work, emotional perceptions were classified into six categories, such as joy, affection, distress, angry, disgust and null. The pre-trained language model named Bidirectional Encoder Representations from Transformers was used to analyze the emotional expression of active users and generate the emotional perception map. Compared with the traditional sentiment analysis model, the Bidirectional Encoder Representations from Transformers has a greater degree of improvement in correctness. Then part-of-speech analysis was applied to the comments extracted to investigate the cause of the emotional perception. In the last, this paper used Lexical Analysis of Chinese, a lexical analysis tool developed by Baidu, for lexical analysis and named entity recognition. In total, 813,633 geotagged social media data and 1619 POI were collected from Shanghai. The main findings were as follows:1) The most popular sign-in locations in Shanghai are concentrated in the inner-city, transportation hubs and important public facilities. 2) The proportion of positive emotions shows an overall decrease with the increase of the distance to the city center. 3) Producers' emotional perception of various activity spaces were mostly positive opinions, so the results of commentary viewpoint extraction were similar.

Key words： deep learning BERT model sign-in map emotion map perception evaluation

收稿日期: 2020-12-09

PACS:

K901

基金资助:国家自然科学基金项目（41471138）

通讯作者: 何丹(1971-),男,云南昆明人,博士,副教授,主要研究方向为城市发展与城市规划。E-mail:dhe@re.ecnu.edu.cn。 E-mail: dhe@re.ecnu.edu.cn

作者简介: 崔璐明(1993-),女,河南新乡人,博士研究生,主要研究方向为城市地理与城市经济。E-mail:lmcui0501@163.com。

引用本文:

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): 121-130,176. CUI Lu-ming, QU Ling-yan, HE Dan. EVALUATING EMOTIONAL PERCEPTION OF SPATIAL HOTSPOTS VIA DEEP LEARNING: A CASE STUDY OF SHANGHAI. HUMAN GEOGRAPHY, 2021, 36(5): 121-130,176.

链接本文:

http://rwdl.xisu.edu.cn/CN/10.13959/j.issn.1003-2398.2021.05.015 或 http://rwdl.xisu.edu.cn/CN/Y2021/V36/I5/121

[1]	Izard C E. Human Emotions[M]. Berlin:Springer Science & Business Media, 2013:1-4.
[2]	Wierzbicka A. Human emotions:Universal or culture-specific?[J/OL]. American Anthropologist, 1986,88(3):584-594.
[3]	Salesses P, Schechtner K, Hidalgo C A. The collaborative image of the city:Mapping the inequality of urban perception[J/OL]. PloS one, 2015, 10(3):e0119352. http://doi.org/10.1371/journal.pone.0119352.
[4]	Golder S A, Macy M W. Diurnal and seasonal mood vary with work, sleep, and daylength across diverse cultures[J]. Science, 2011, 333(6051):1878-1881.
[5]	张圆刚,余向洋,Wong IpKin Anthony,等.古村落景区游客拥挤感知维度与游憩情绪影响机制研究——以西递、宏村为例[J].人文地理,2018,33(2):138-146.[Zhang Yuangang, Yu Xiangyang, Wong IpKin Anthony, et al. Research on the influential mechanism between the tourists' crowding perception and emotions for recreation in ancient village scenic spot:A case study of Xidi and Hongcun ancient villages[J]. Human Geography, 2018,33(2):138-146.]
[6]	Goodchild M F. Space, place and health[J]. Annals of GIS, 2015, 21(2):97-100.
[7]	Kaplan R, Kaplan S. The Experience of Nature:A Psychological Perspective[M]. Cambridge:Cambridge University Press, 1989:9-27.
[8]	Lynch K, Lynch K R. The Image of the City[M]. Boston:MIT Press, 1960:91-117.
[9]	Nasar J L. The evaluative image of the city[J]. Journal of the American Planning Association, 1990,56(1):41-53.
[10]	Tuan Y F. Space and Place:The Perspective of Experience[M]. Minneapolis:University of Minnesota Press, 1977:1-7.
[11]	蹇嘉,甄峰,席广亮,等.西方情绪地理学研究进展与启示[J].世界地理研究,2016,25(2):123-136.[Jian Jia, Zhen Feng, Xi Guangliang, et al. A review on emotional geography:Its progress and enlightenment[J]. World Regional Studies, 2016,25(2):123-136.]
[12]	朱竑,高权.西方地理学"情感转向" 与情感地理学研究述评[J].地理研究,2015,34(7):1394-1406.[Zhu Hong, Gao Quan. Review on "emotional turn" and emotional geographies in recent western geography[J]. Geographical Research, 2015,34(7):1394-1406.]
[13]	高权,钱俊希. "情感转向" 视角下地方性重构研究——以广州猎德村为例[J].人文地理,2016,31(4):33-41.[Gao Quan, Qian Junxi. Negotiating place-restructuring from the perspective of emotional geographies:A case study of Liede village, Guangzhou[J]. Human Geography, 2016,31(4):33-41.]
[14]	梁璐,代莉,田嘉申,等.情感地理学视角下纪念性恐惧景观地游客体验特征分析——以5·12汶川特大地震纪念馆为例[J].西北大学学报(自然科学版),2018,48(6):884-892.[Liang Lu, Dai Li, Tian Jiashen, et al. The characteristics of tourist experience in memorial landscapes of fear from the perspective of emotional geography:The case of 5·12 Wenchuan Earthquake Memorial Museum[J]. Journal of Northwest University (Natural Science Edition), 2018, 48(6):884-892.]
[15]	Plunz R A, Zhou Y, Vintimilla M I C, et al. Twitter sentiment in New York city parks as measure of well-being[J]. Landscape and Urban Planning, 2019,189:235-246.
[16]	易峥,李继珍,冷炳荣,等.基于微博语义分析的重庆主城区风貌感知评价[J].地理科学进展,2017,36(9):1058-1066.[Yi Zheng, Li Jizhen, Leng Bingrong, et al. Perception and evaluation of cityscape characteristics using semantic analysis on Microblog in the main urban area of Chongqing municipality[J]. Progress in Geography, 2017,36(9):1058-1066.]
[17]	Shelton T, Poorthuis A, Zook M. Social media and the city:Rethinking urban socio-spatial inequality using user-generated geographic information[J]. Landscape and Urban Planning, 2015,142:198-211.
[18]	汪芳,严琳,熊忻恺,等.基于游客认知的历史地段城市记忆研究——以北京南锣鼓巷历史地段为例[J].地理学报,2012,67(4):545-556.[Wang Fang, Yan Lin, Xiong Xinkai, et al. A study on tourist cognition of urban memory in historic sites:A case study of Alley Nanluogu historic site in Beijing[J]. Acta Geographica Sinica, 2012, 67(4):545-556.]
[19]	梁嘉祺,姜珊,陶犁.基于网络游记语义分析和GIS可视化的游客时空行为与情绪关系实证研究——以北京市为例[J].人文地理, 2020,35(2):152-160.[Liang Jiaqi, Jiang Shan, Tao Li. Empirical research on the relationship between spatial-temporal behavior and emotion of tourists based on semantic analysis of online travel blogs and GIS visualization:A case of Beijing[J]. Human Geography, 2020,35(2):152-160.]
[20]	孙晓东,倪荣鑫.中国邮轮游客的产品认知、情感表达与品牌形象感知——基于在线点评的内容分析[J].地理研究,2018,37(6):1159-1180.[Sun Xiaodong, Ni Rongxin. Chinese cruisers' product cognition, emotional expression and brand image perception:A Web content analysis[J]. Geographical Research, 2018,37(6):1159-1180.]
[21]	王波,甄峰,张浩.基于签到数据的城市活动时空间动态变化及区划研究[J].地理科学,2015,35(2):151-160.[Wang Bo, Zhen Feng, Zhang Hao. The dynamic changes of urban space-time activity and activity zoning based on check-in data in Sina Web[J]. Progress in Geography, 2015,35(2):151-160.]
[22]	余凯,贾磊,陈雨强,等.深度学习的昨天、今天和明天[J].计算机研究与发展,2013,50(9):1799-1804.[Yu Kai, Jia Lei, Chen Yuqiang, et al. Deep learning:Yesterday, today, and tomorrow[J]. Journal of Computer Research and Development, 2013,50(9):1799-1804.]
[23]	张郴,黄震方,张捷,等.基于机器学习的南京市旅游地个性及其文化景观表征[J].地理学报,2017,72(10):1886-1903.[Zhang Chen, Huang Zhenfang, Zhang Jie, et al. Urban tourism destination personality and its cultural landscape representation via machine learning:A case study of Nanjing[J]. Acta Geographica Sinica, 2017, 72(10):1886-1903.]
[24]	何宛余,李春,聂广洋,等.深度学习在城市感知的应用可能——基于卷积神经网络的图像判别分析[J].国际城市规划,2019,34(1):8-17.[He Wanyu, Li Chun, Nie Guangyang, et al. The latent application of deep learning in urban perception:Image discrimination analysis by convolutional neural network[J]. Urban Planning International, 2019,34(1):8-17.]
[25]	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.
[26]	奚雪峰,周国栋.面向自然语言处理的深度学习研究[J].自动化学报,2016,42(10):1445-1465.[Xi Xuefeng, Zhou Guodong. A Survey on deep learning for natural language processing[J]. Acta Automatica Sinica, 2016,42(10):1445-1465.]
[27]	乐国安,董颖红.情绪的基本结构:争论、应用及其前瞻[J].南开学报(哲学社会科学版),2013(1):140-150.[Yue Guoan, Dong Yinghong. On the categorical and dimensional approaches of the theories of the basic structure of emotions[J]. Nankai Journal (Philosophy, Literature and Social Science Edition), 2013(1):140-150.]
[28]	Zhou H, Huang M, Zhang T, et al. Emotional chatting machine:Emotional conversation generation with internal and external memory[C]. New Orleans, Louisiana, USA:Proceedings of the AAAI Conference on Artificial Intelligence, 2018:730-738.
[29]	Devlin J, Chang M W, Lee K, et al. BERT:Pre-training of deep bidirectional transformers for language understanding[C]. Minneapolis, Minnesota, USA:Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics, 2019:4171-4186.
[30]	李舟军,范宇,吴贤杰.面向自然语言处理的预训练技术研究综述[J]. 计算机科学,2020,47(3):162-173.[Li Zhoujun, Fan Yu, Wu Xianjie. Survey of natural language processing pre-training techniques[J]. Computer Science, 2020,47(3):162-173.]
[31]	Ma K, Jiang B. Voice of urban park visitors:Exploring destination attributes influencing behavioural intentions through online review mining[J/OL]. Complex & Intelligent Systems, 2020. https://doi.org/10.1007/s40747-020-00223-7.
[32]	鲁仕维,方志祥,萧世伦,等.城市群体移动模式研究中空间尺度影响的定量分析[J].武汉大学学报(信息科学版),2016,41(9):1199-1204.[Lu Shiwei, Fang Zhixiang, Shaw Shihlung, et al. Quantitative analysis of the effects of spatial scales on intra-urban human mobility[J]. Geomatics and Information Science of Wuhan University, 2016,41(9):1199-1204.]
[33]	陈江平,张瑶,余远剑.空间自相关的可塑性面积单元问题效应[J]. 地理学报,2011,66(12):1597-1606.[Chen Jiangping, Zhang Yao, Yu Yuanjian. Effect of MAUP in spatial autocorrelation[J]. Acta Geographica Sinica, 2011,66(12):1597-1606.]
[34]	齐丽丽,柏延臣.社会经济统计数据热点探测的MAUP效应[J].地理学报,2012,67(10):1317-1326.[Qi Lili, Bo Yanchen. MAUP effects on the detection of spatial hot spots in socio-economic statistical data[J]. Acta Geographica Sinica, 2012,67(10):1317-1326.]
[35]	Wu L, Zhi Y, Sui Z, et al. Intra-urban human mobility and activity transition:Evidence from social media check-in data[J/OL]. PloS One, 2014,9(5):e97010. https://doi.org/10.1371/journal.pone.0097010.
[36]	陈映雪.居民情绪与建成环境关系研究及规划应用初探[D].南京:南京大学,2015:25-36.[Chen Yingxue. Thesis:A Study of Relevance Between Residents' Emotions and Built Environment:A Preliminary Research for Emotion-based Planning[D]. Nanjing:Nanjing University, 2015:25-36.]
[37]	Williams S J. Emotion and Social Theory:Corporeal Reflections on the (ir) Rational[M]. London:Sage, 2001:1-28.
[38]	Hoelscher C, Schinazi V R, Thrash T, et al. Theoretical and methodological challenges for cognitive research in the built environment[M]//Future Cities Laboratory:Indicia 01. Zurich, Switzerland:Lars Muller Publishers, 2017:133-140.
[39]	刘坚,孟斌,陈思宇,等.多源大数据下的北京市居民就餐活动与城市空间关系探究[J].人文地理,2021,36(2):63-72,183.[Liu Jian, Meng Bin, Chen Siyu, et al. Study on the relationship between dining activities of Beijing residents and urban space based on multisource big data[J]. Human Geography, 2021,36(2):63-72,183.]
[40]	新浪微博数据中心.2018微博用户发展报告[EB/OL].(2019-03-15)[2020-12-09]. https://data.weibo.com/report/index.[Weibo Data Center. Weibo statistics, user counts and facts report[EB/OL]. (2019-03-15)[2020-12-09]. https://data.weibo.com/report/index.]