Understanding Citizens’emotion States under the Urban Livability Environment through Social Media Data: a Case Study of Wuhan

doi:10.11947/j.JGGS.2022.0206

摘要/Abstract

Abstract:

It is recognized that a city with a livable environment can bring happiness to residents. In this study, we explored the social media users’ emotional states in their current living spaces and found out the relationship between the social media users’ emotions and urban livability. We adopt six urban livability indicators (including education, medical services, public facilities, leisure places, employment, and transportation) to construct city livable indices. Also, the Analytic Hierarchy Process (AHP) spatial statistic method is applied to identify and analyze the different habitable regions of Wuhan City. In terms of citizen’s emotion analysis, we use Long Short-Term Memory (LSTM) neural network to analyze the Weibo text and obtain the Weibo users’sentiment scores. The correlation analysis of residents’ emotions and city livability results shows a positive correlation between the livable city areas (i.e., the area with higher livable ranking indices) and Weibo users’ sentiment scores (with a Pearson correlation coefficient of 0.881 and P-Value of 0.004). In other words, people who post Weibo in high livability areas of Wuhan express more positive emotional states. Still, emotion distribution varies in different regions, which is mainly caused by people’s distribution and the diversity of the city’s functional areas.

Key words: urban livability, sentiment analysis, Sina Weibo, Analytic Hierarchy Process, natural language processing, Long Short-Term Memory

. [J]. 测绘学报（英文版）, 2022, 5(2): 49-59.

Lai CHEN,Chaogui KANG,Chao YANG. Understanding Citizens’emotion States under the Urban Livability Environment through Social Media Data: a Case Study of Wuhan[J]. Journal of Geodesy and Geoinformation Science, 2022, 5(2): 49-59.

图/表 15

参考文献 42

[1]	WU Zhen, CHEN Ruishan, MEADOWS M E, et al. Changing urban green spaces in Shanghai: trends, drivers and policy implications[J]. Land Use Policy, 2019, 87: 104080. doi: 10.1016/j.landusepol.2019.104080
[2]	HIGASA T. Urban planning[M]. Tokyo: Kioritz Corporation Press, 1977.
[3]	ZHANG Wenzhong. The core framework of the livable city construction[J]. Geographical Research, 2016, 35(2): 205-213. doi: 10.11821/dlyj201602001
[4]	LIANG Li, DENG Xiangzheng, WANG Pei, et al. Assessment of the impact of climate change on cities livability in China[J]. Science of the Total Environment, 2020, 726: 138339. doi: 10.1016/j.scitotenv.2020.138339
[5]	ZHU Likai, GUO Yuanyuan, ZHANG Chi, et al. Assessing community-level livability using combined remote sensing and internet-based big geospatial data[J]. Remote Sensing, 2020, 12(24): 4026. doi: 10.3390/rs12244026
[6]	KAKLAUSKAS A, ZAVADSKAS E K, RADZEVICIENE A, et al. Quality of city life multiple criteria analysis[J]. Cities, 2018, 72: 82-93. doi: 10.1016/j.cities.2017.08.002
[7]	CONGER B W. On livability, liveability and the limited utility of quality-of-life rankings[J]. SPP Communique, 2015, 7(4):1-8.
[8]	OKULICZ-KOZARYN A. City life: rankings (livability) versus perceptions (satisfaction)[J]. Social Indicators Research, 2013, 110(2): 433-451. doi: 10.1007/s11205-011-9939-x
[9]	KASHEF M. Urban livability across disciplinary and profes-sional boundaries[J]. Frontiers of Architectural Research, 2016, 5(2): 239-253. doi: 10.1016/j.foar.2016.03.003
[10]	ZHU Zhenjun, LI Zhigang, CHEN Hongsheng, et al. Subjective well-being in China: how much does commuting matter?[J]. Transportation, 2019, 46(4): 1505-1524. doi: 10.1007/s11116-017-9848-1
[11]	LIN Sainan, LI Zhigang. Residential satisfaction of migrants in Wenzhou, an ordinary city of China[J]. Habitat International, 2017, 66: 76-85. doi: 10.1016/j.habitatint.2017.05.004
[12]	REN Honghao, FOLMER H. Determinants of residential satisfaction in urban China: a multi-group structural equation analysis[J]. Urban Studies, 2017, 54(6): 1407-1425. doi: 10.1177/0042098015627112
[13]	ZHAN Dongsheng, KWAN M P, ZHANG Wenzhong, et al. Assessment and determinants of satisfaction with urban livability in China[J]. Cities, 2018, 79: 92-101. doi: 10.1016/j.cities.2018.02.025
[14]	ETTEMA D, SMAJIC I. Walking, places and wellbeing[J]. The Geographical Journal, 2015, 181(2): 102-109. doi: 10.1111/geoj.12065
[15]	CATTELL V, DINES N, GESLER W, et al. Mingling, observing, and lingering: everyday public spaces and their implications for well-being and social relations[J]. Health & Place, 2008, 14(3): 544-561.
[16]	MACKERRON G, MOURATO S. Happiness is greater in natural environments[J]. Global Environmental Change, 2013, 23(5): 992-1000. doi: 10.1016/j.gloenvcha.2013.03.010
[17]	JIM C Y, CHEN W Y. Perception and attitude of residents toward urban green spaces in Guangzhou (China)[J]. Environmental Management, 2006, 38(3): 338-349. doi: 10.1007/s00267-005-0166-6
[18]	GUNNARSSON B, KNEZ I, HEDBLOM M, et al. Effects of biodiversity and environment-related attitude on perception of urban green space[J]. Urban Ecosystems, 2017, 20(1): 37-49. doi: 10.1007/s11252-016-0581-x
[19]	HEDBLOM M, GUNNARSSON B, IRAVANI B, et al. Reduction of physiological stress by urban green space in a multisensory virtual experiment[J]. Scientific Reports, 2019, 9: 10113. doi: 10.1038/s41598-019-46099-7
[20]	YUE Lin, CHEN Weitong, LI Xue, et al. A survey of sentiment analysis in social media[J]. Knowledge and Information Systems, 2019, 60(2): 617-663. doi: 10.1007/s10115-018-1236-4
[21]	YOUNIS E M G. Sentiment analysis and text mining for social media microblogs using open source tools: an empirical study[J]. International Journal of Computer Applications, 2015, 112(5): 44-48.
[22]	ZUNIC A, CORCORAN P, SPASIC I. Sentiment analysis in health and well-being: systematic review[J]. JMIR Medical Informatics, 2020, 8(1): e16023. doi: 10.2196/16023
[23]	KHAN R, SHRIVASTAVA P, KAPOOR A, et al. Social media analysis with AI: sentiment analysis techniques for the analysis of twitter COVID-19 data[J]. Journal of Critical Reviews, 2020, 7(9): 2761-2774.
[24]	CAMBRIA E, LI Yang, XING F Z, et al. SenticNet 6: ensemble application of symbolic and subsymbolic AI for sentiment analysis[C]//Proceedings of the 29th ACM International Conference on Information & Knowledge Management. [S.l.]: ACM, 2020: 105-114.
[25]	ZHU Likai, GUO Yuanyuan, ZHANG Chi, et al. Assessing community-level livability using combined remote sensing and internet-based big geospatial data[J]. Remote Sensing, 2020, 12(24): 4026. doi: 10.3390/rs12244026
[26]	HEMMATIAN F, SOHRABI M K. A survey on classification techniques for opinion mining and sentiment analysis[J]. Artificial Intelligence Review, 2019, 52(3): 1495-1545. doi: 10.1007/s10462-017-9599-6
[27]	TSYTSARAU M, PALPANAS T. Survey on mining subjective data on the web[J]. Data Mining and Knowledge Discovery, 2012, 24(3): 478-514. doi: 10.1007/s10618-011-0238-6
[28]	GUPTA I, JOSHI N. Feature-based twitter sentiment analysis with improved negation handling[J]. IEEE Transactions on Computational Social Systems, 2021, 8(4): 917-927. doi: 10.1109/TCSS.2021.3069413
[29]	PANDEY A C, RAJPOOT D S, SARASWAT M. Twitter sentiment analysis using hybrid cuckoo search method[J]. Information Processing & Management, 2017, 53(4): 764-779. doi: 10.1016/j.ipm.2017.02.004
[30]	KUMAR A, SRINIVASAN K, CHENG W H, et al. Hybrid context enriched deep learning model for fine-grained sentiment analysis in textual and visual semiotic modality social data[J]. Information Processing & Management, 2020, 57(1): 102141. doi: 10.1016/j.ipm.2019.102141
[31]	WANG Gang, ZHANG Zhu, SUN Jianshan, et al. POS-RS: a random subspace method for sentiment classification based on part-of-speech analysis[J]. Information Processing & Management, 2015, 51(4): 458-479. doi: 10.1016/j.ipm.2014.09.004
[32]	PLUNZ R A, ZHOU Yijia, 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. doi: 10.1016/j.landurbplan.2019.04.024
[33]	ILIEVA R T, MCPHEARSON T. Social-media data for urban sustainability[J]. Nature Sustainability, 2018, 1(10): 553-565. doi: 10.1038/s41893-018-0153-6
[34]	LEE K Y. Factors influencing urban livability in Seoul, Korea: urban environmental satisfaction and neighborhood relations[J]. Social Sciences, 2021, 10(4): 138. doi: 10.3390/socsci10040138
[35]	GONG Jianya, JI Shunping. Photogrammetry and deep learning[J]. Journal of Geodesy and Geoinformation Science, 2018, 47(6): 693-704. DOI: 10.11947/j.AGCS.2018.20170640. doi: 10.11947/j.AGCS.2018.20170640
[36]	LI Mingxiao, ZHANG Hengcai, QIU Peiyuan, et al. A moving object trajectory prediction algorithm based on fuzzy long-term and short-term neural network[J]. Acta Geodaetica et Cartographica Sinica, 2018, 47(12): 1660-1669. DOI: 10.11947/j.AGCS.2018.20170268. doi: 10.11947/j.AGCS.2018.20170268
[37]	LIU Qinhao, ZHANG Yonghong, DENG Min, et al. Time series prediction method of large-scale surface subsidence based on deep learning[J]. Acta Geodaetica et Cartographica Sinica, 2021, 50(3): 396-404. DOI: 10.11947/j.AGCS.2021.20200038. doi: 10.11947/j.AGCS.2021.20200038
[38]	LI Jing, LIU Haiyan, GUO Wenyue, et al. A spatio-temporal network for human activity prediction based on deep learning[J]. Acta Geodaetica et Cartographica Sinica, 2021, 50(4): 522-531. DOI: 10.11947/j.AGCS.2021.20200230. doi: 10.11947/j.AGCS.2021.20200230
[39]	CAI Wei, CAI Hongxin, WANG Haoxian. The spatial evaluation of urban residential suitability based on ArcGIS[J]. Geomatics & Spatial Information Technology, 2014, 37(9): 161-164.
[40]	HU Huiming, QIAN Haizhong, HE Haiwei, et al. Auto-selection of areal habitation based on analytic hierarchy process[J]. Acta Geodaetica et Cartographica Sinica, 2016, 45(6): 740-746. DOI: 10.11947/j.AGCS.2016.20150078. doi: 10.11947/j.AGCS.2016.20150078
[41]	SAATY T L. Decision making—the analytic hierarchy and network processes (AHP/ANP)[J]. Journal of Systems Science and Systems Engineering, 2004, 13(1): 1-35. doi: 10.1007/s11518-006-0151-5
[42]	Jieba: Chinese Text Segmentation[EB/OL].[2022-04-15]. https://github.com/fxsjy/jieba .

	Indicators	Contents (Part of)
Urban livability indicators	Education	Primary school, high school, college
	Medical services	hospital, clinic
	Public facilities	Park, museum, green land
	Leisure places	Entertainment venues, leisure places
	Employment	State-owned enterprise, private enterprise
	Transportation	Road networks

(a) Scores for each factor
Target layer(A)		Standard level (B)	Points
City livability		Transportation(B1)	6
		Leisure places(B2)	3
		Public facilities(B3)	6
		Education(B4)	3
		Medical and health(B5)	3
		Employment(B6)	6
(b) The judgment criteria for relative importance
Points	Meaning
1	It means that the two factors are equally important
3	Indicates that the two factors are slightly more important than the former
5	Indicates that the two factors are significantly more important than the former
7	It means that the two factors are more important than the former
9	Indicates that the two factors are extremely important than the former
2、4、6、8	Represents the intermediate value of the above judgment adjacent

Factor	Influence distance/m
Transportation	300
Leisure places	500
Public facilities	400
Education	500
Medical services	500
Employment	1000

Parameter	Parameter value
Emotional threshold	0.39
Dropout	0.5
batch_size	128
train_num	120
max_len	100
min_count	5

Original Weibo text	Emotional label	Sentiment value
01. Someone still remembers my birthday. Although it is a trivial matter, it is still quite touching.	Pos	0.90
02. It’s been a long time since I drank coffee, it’s a bit uncomfortable http:t.cn/R2WJAOc	Neg	0.03
03. My friend went to Hokkaido to take photos in Japan. It’s so beautiful, I really want to go to Japan... [Poor] http://t.cn/R2dUAgX	Pos	0.76
04. Good luck in July [rabbit]#hello July # http://t.cn/R2dUAD3	Pos	0.99
05. The random process reveals a profound truth in life, the theorem is understood, but still unable to solve the problem. http://t.cn/R2dUAgX	Neg	0.03
06.Commemorating our passing freshman...http://t.cn/R2dUAgX 08.Walking in the wind, the sunshine today is suddenly so gentle. http://t.cn/R2dUAdW	Pos	0.3
07. Finally finished the exam, I will go for an internship in September [bye bye] http://t.cn/R2W6Cf2	Pos	0.4
08. I get off work at this point every day, I’m so heartbroken [tears][tears][tears] walked one hour late http:t.cn/R2WizXv	Neg	0.15
09. The most annoying subject to remember! It’s better to come and die with a few big calculations http:t.cn/R2WJAOc	Neg	0.08
10. Starving to death, I can finally start [Love you] http://t.cn/R2WJAOc	Pos	0.91