Environmental characteristics affect how individuals perceive an environment, and the emotions created by environmental characteristics originate from subjective feelings. Despite cities being crucial human living spaces, few studies have used geospatial technology to determine the relationship between urban environments and emotions. Therefore, this study explored the effects of urban environmental characteristics on emotions by surveying 50 sampling areas in Taipei City. Deep learning was performed with the DeepLab V3 architecture in combination with the LaDeco tool to identify environmental characteristics in over 200,000 Google Street View (GSV) images. These characteristics were divided into five major types, namely, vegetationscapes, waterscapes, streetscapes, landformscapes, and archiscapes, then further classified into 53 categories. To identify the emotions related to urban environments, 2090 participants who were asked to view GSV videos and report their emotions. Subsequent multiple regression analyses revealed that in vegetationscapes and waterscapes, grass and fountains induced positive emotions, whereas trees reduced negative emotions. Meanwhile, dense, old, and disorganized buildings, such as hovels, reduced positive emotions. The results of this study may serve as a reference to help designers create an urban environment that fosters positive emotions.
AshfieldSDonelleLSmithM, et al. (2024) Challenges and opportunities in recruiting research participants using Facebook: lessons learned from an exemplar study. Canadian Journal of Nursing Research56(3): 247–256. DOI: 10.1177/08445621231207546.
2.
BallasDDorlingD (2012) Oxford Handbook of Happiness: The Geography of Happiness. Oxford University Press.
3.
BaumannHGrêt-RegameyA (2024) Exploring the interplay of urban form and greenery in residents' affective and cognitive responses. Urban Forestry and Urban Greening101: 128553. DOI: 10.1016/j.ufug.2024.128553.
4.
BenabbouRLeeH (2019) Exploring the evolution of urban emotions in the City of Seoul using social media information. International Journal of Knowledge-Based Development10(3): 232–248. DOI: 10.1504/IJKBD.2019.103208.
5.
BermanMGKrossEKrpanKM, et al. (2012) Interacting with nature improves cognition and affect for individuals with depression. Journal of Affective Disorders140(3): 300–305. DOI: 10.1016/j.jad.2012.03.012.
6.
BiljeckiFItoK (2021) Street view imagery in urban analytics and GIS: a review. Landscape and Urban Planning215: 104217. DOI: 10.1016/j.landurbplan.2021.104217.
7.
BorchCBöhmeGEliassonO, et al. (2014) Architectural Atmospheres. Birkhäuser.
8.
BoulianneS (2015) Social media use and participation: a meta-analysis of current research. Information, Communication & Society18: 524–538. DOI: 10.1080/1369118X.2015.1008542.
9.
ButtazzoniADeanJMinakerL (2023) Urban design and adolescent mental health: a qualitative examination of adolescent emotional responses to pedestrian- and transit-oriented design and cognitive architecture concepts. Health & Place76: 102825. DOI: 10.1016/j.healthplace.2022.102825.
10.
ChenL-CZhuYPapandreouG, et al. (2018) Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Computer Vision and Pattern Recognition ECCV 2018. Berlin, Germany: Springer. DOI: 10.48550/arXiv.1802.02611.
11.
ChenCLiHLuoW, et al. (2022) Predicting the effect of street environment on residents' mood states in large urban areas using machine learning and street view images. The Science of the Total Environment816(10): 151605. DOI: 10.1016/j.scitotenv.2021.151605.
12.
ChenCLinXWuY, et al. (2024) How do residents perceive ecosystem service benefits received from urban streets? A case study of Guangzhou, China. Journal of Cleaner Production449: 141554. DOI: 10.1016/j.jclepro.2023.141554.
13.
ChiangYCLiuHHLiD, et al. (2023a) Quantification through deep learning of sky view factor and greenery on urban streets during hot and cool seasons. Landscape and Urban Planning232: 104679. DOI: 10.1016/j.landurbplan.2022.104679.
14.
ChiangYCWengPYLiD, et al. (2023b) Quantity and quality: role of vegetation in park visitation and physical activity. Landscape and Ecological Engineering19: 337–350. DOI: 10.1007/s11355-023-00558-6.
15.
ClarkePAilshireJMelendezR, et al. (2010) Using Google Earth to conduct a neighborhood audit: reliability of a virtual audit instrument. Health & Place16(6): 1224–1229. DOI: 10.1016/j.healthplace.2010.08.007.
16.
CohenJCohenPWestSG, et al. (2003) Applied Multiple Regression/ Correlation Analysis for the Behavioral Sciences. 3rd edition. New York: Routledge.
17.
ColeDNHallTE (2010) Experiencing the restorative components of wilderness environments: does congestion interfere and does length of exposure matter?Environment and Behavior42(6): 806–823. DOI: 10.1177/0013916509347248.
CoxDTCShanahanDFHudsonHL, et al. (2017) Doses of nearby nature simultaneously associated with multiple health benefits. International Journal of Environmental Research and Public Health14(2): 172. DOI: 10.3390/ijerph14020172.
20.
DaiLZhengCDongZ, et al. (2021) Analyzing the correlation between visual space and residents’ psychology in Wuhan, China using street-view images and deep-learning technique. City and Environment Interactions11: 100069. DOI: 10.1016/j.cacint.2021.100069.
21.
DengLLiXLuoH, et al. (2020) Empirical study of landscape types, landscape elements and landscape components of the urban park promoting physiological and psychological restoration. Urban Forestry and Urban Greening48: 126488. DOI: 10.1016/j.ufug.2019.126488.
22.
Department of Household Registration (2023) Population Data Quarterly Publication. Taiwan: Ministry of the Interior. https://www.ris.gov.tw/app/portal/346 (Accessed 1 Aug 2023).
23.
DunneJHvon BenzonNWhittleR (2022) Facebook as a platform for collecting women’s birth stories: supporting emotional connections between researchers and participants. Emotion, Space and Society42: 100863. DOI: 10.1016/j.emospa.2021.100863.
24.
d’HauteserreA (2015) Affect theory and the attractivity of destinations. Annals of Tourism Research55: 77–89. DOI: 10.1016/j.annals.2015.09.001.
25.
EllawayAMorrisGCurticeJ, et al. (2009) Associations between health and different types of environmental incivility: a Scotland-wide study. Public Health123(11): 708–713. DOI: 10.1016/j.puhe.2009.09.019.
26.
EllisonNBSteinfieldCLampeC (2007) The benefits of Facebook “friends:” Social capital and college students’ use of online social network sites. Journal of Computer-Mediated Communication12: 1143–1168. DOI: 10.1111/j.1083-6101.2007.00367.x.
27.
FangYNTianJNamaitiA, et al. (2024) Visual aesthetic quality assessment of the streetscape from the perspective of landscape-perception coupling. Environmental Impact Assessment Review106: 107535. DOI: 10.1016/j.eiar.2024.107535.
28.
FengYDuSMyintSW, et al. (2019) Do urban functional zones affect land surface temperature differently? A case study of Beijing, China. Remote Sensing11(15): 1802. DOI: 10.3390/rs111518022.
29.
GasconMCirachMvillarreal MartinezD, et al. (2016) Normalized difference vegetation index (NDVI) as a marker of surrounding greenness in epidemiological studies: the case of Barcelona city. American. Urban Forestry and Urban Greening19: 88–94. DOI: 10.1016/j.ufug.2016.07.001.
30.
GongFZengZZhangF, et al. (2021) Mapping sky, tree, and building view factors of street canyons in a high-density urban environment. Building and Environment134(15): 155–167. DOI: 10.1016/j.buildenv.2018.02.042.
31.
HanXWangLSeoSH, et al. (2022) Measuring perceived psychological stress in urban built environments using Google Street View and deep learning. Frontiers in Public Health10: 1–18. DOI: 10.3389/fpubh.2022.891736.
32.
HartigTEvansGWJamnerLD, et al. (2003) Tracking restoration in natural and urban field settings. Journal of Environmental Psychology23(2): 109–123. DOI: 10.1016/S0272-4944(02)00109-3.
33.
HauthalEBurghardtD (2016) Mapping space-related emotions out of user-generated photo metadata considering grammatical issues. The Cartographic Journal53(1): 78–90. DOI: 10.1179/1743277414Y.0000000094.
34.
HeJZhangJYaoY, et al. (2023) Extracting human perceptions from street view images for better assessing urban renewal potential. Cities134: 104189. DOI: 10.1016/j.cities.2023.104189.
35.
Herrmann-LuneckeMGMoraRVejaresP (2021) Perception of the built environment and walking in pericentral neighbourhoods in Santiago, Chile. Travel Behaviour and Society23: 192–206. DOI: 10.1016/j.tbs.2021.01.002.
36.
HigginsSLThomasFGoldsmithB, et al. (2019) Urban freshwaters, biodiversity, and human health and well-being: setting an interdisciplinary research agenda. WIREs Water6(2): e1339. DOI: 10.1002/wat2.1339.
37.
HoL (2023) LaDeco: a tool to analyze visual landscape elements. Ecological Informatics78: 102289. DOI: 10.1016/j.ecoinf.2023.102289.
38.
HoyleHHitchmoughJJorgensenA (2017) All about the “wow factor”? The relationships between aesthetics, restorative effect and perceived biodiversity in designed urban planting. Landscape and Urban Planning164: 109–123. DOI: 10.1016/j.landurbplan.2017.03.011.
39.
HuangQYangMJaneH, et al. (2020) Trees, grass, or concrete? The effects of different types of environments on stress reduction. Landscape and Urban Planning193: 103654. DOI: 10.1016/j.landurbplan.2019.103654.
40.
HunterMRAskarinejadA (2015) Designer’s approach for scene selection in tests of preference and restoration along a continuum of natural to manmade environments. Frontiers in Psychology6: 1228. DOI: 10.3389/fpsyg.2015.01228.
41.
IzardCE (2013) Human Emotions. New York: Plenum Press.
42.
JacobsJ (1961) The Death and Life of Great American Cities. New York: The Random House.
43.
JeonJWooA (2023) Deep learning analysis of street panorama images to evaluate the streetscape walkability of neighborhoods for subsidized families in Seoul, Korea. Landscape and Urban Planning230: 104631. DOI: 10.1016/j.landurbplan.2022.104631.
44.
JiangBChangCSullivanWC (2014) A dose of nature: tree cover, stress reduction, and gender differences. Landscape and Urban Planning132: 26–36. DOI: 10.1016/j.landurbplan.2014.08.005.
45.
KabischNQureshiSHaaseD (2015) Human–environment interactions in urban green spaces - a systematic review of contemporary issues and prospects for future research. Environmental Impact Assessment Review50: 25–34. DOI: 10.1016/j.eiar.2014.08.007.
46.
KuoFESullivanWC (2001) Environment and crime in the inner city: does vegetation reduce crime?Environment and Behavior33(3): 343–367. DOI: 10.1177/0013916501333002.
47.
LiXZhangCLiW, et al. (2015) Assessing street-level urban greenery using Google Street View and a modified green view index. Urban Forestry and Urban Greening14(3): 675–685. DOI: 10.1016/j.ufug.2015.06.006.
48.
LiHPengJJiaoY, et al. (2022) Experiencing urban green and blue spaces in urban wetlands as a nature-based solution to promote positive emotions. Forests13(3): 473. DOI: 10.3390/f13030473.
49.
LiMLiuRLiX, et al. (2024) The effect of perceived real-scene environment of a river in a high-density urban area on emotions. Land13(1): 35. DOI: 10.3390/land13010035.
50.
LinYWoodSALawlerJJ (2022) The relationship between natural environments and subjective well-being as measured by sentiment expressed on Twitter. Landscape and Urban Planning227: 104539. DOI: 10.1016/j.landurbplan.2022.104539.
51.
Loukaitou-SiderisAEhrenfeuchtR (2011) Sidewalks: Conflict and Negotiation over Public Space. Cambridge: The MIT Press.
52.
LöwM (2016) The Sociology of Space: Materiality, Social Structures, and Action. London: Palgrave Macmillan.
53.
LuY (2019) Using Google Street View to investigate the association between street greenery and physical activity. Landscape and Urban Planning191: 103435. DOI: 10.1016/j.landurbplan.2018.08.029.
54.
LuYChenH (2024) Using google street view to reveal environmental justice: assessing public perceived walkability in macroscale city. Landscape and Urban Planning244: 104995. DOI: 10.1016/j.landurbplan.2023.104995.
MaHLiJYeX (2025) Deep learning meets urban design: assessing streetscape aesthetic and design quality through AI and cluster analysis. Cities162: 105939. DOI: 10.1016/j.cities.2025.105939.
57.
MeenarMRMandaranoLA (2021) Using photovoice and emotional maps to understand transitional urban neighborhoods. Cities118: 103353. DOI: 10.1016/j.cities.2021.103353.
58.
MeenarMPánekJKitsonJ, et al. (2025) Mapping the emotional landscapes of parks in post-industrial communities enduring environmental injustices: potential implications for biophilic city planning. Cities158: 105692. DOI: 10.1016/j.cities.2024.105692.
59.
Ministry of the Interior (2020) Statistical Yearbook of Interior Republic of China. Taipei. Ministry of the Interior Republic of China.
60.
MorrisEAGuerraE (2015) Mood and mode: does how we travel affect how we feel?Transportation42: 25–43. DOI: 10.1007/s11116-014-9521-x.
61.
OdeAFryGTveitMS, et al. (2009) Indicators of perceived naturalness as drivers of landscape preference. Journal of Environmental Management90: 375–383. DOI: 10.1016/j.jenvman.2007.10.013.
62.
QiuWZhangZLiuX, et al. (2022) Subjective or objective measures of street environment, which are more effective in explaining housing prices?Landscape and Urban Planning221: 104358. DOI: 10.1016/j.landurbplan.2022.104358.
63.
RapuanoMRuotoloFRuggieroG, et al. (2022) Spaces for relaxing, spaces for recharging: how parks affect people's emotions. Journal of Environmental Psychology81: 101809. DOI: 10.1016/j.jenvp.2022.101809.
64.
RichardsonEPearceJMitchellR, et al. (2010) The association between green space and cause-specific mortality in urban New Zealand: an ecological analysis of green space utility. BMC Public Health10: 240. DOI: 10.1186/1471-2458-10-240.
65.
RossettiTLobelHRoccoV, et al. (2019) Explaining subjective perceptions of public spaces as a function of the built environment: a massive data approach. Landscape and Urban Planning181: 169–178. DOI: 10.1016/j.landurbplan.2018.09.020.
66.
RuanYZouYChenM, et al. (2021) Monitoring the spatiotemporal trajectory of urban area hotspots using the SVM regression method based on NPP-VIIRS imagery. ISPRS International Journal of Geo-Information10(6): 415. DOI: 10.3390/ijgi10060415.
67.
RussellJAPrattG (1980) A description of the affective quality attributed to environments. Journal of Personality and Social Psychology38(2): 311–322. DOI: 10.1037/0022-3514.38.2.311.
68.
SalessesPSchechtnerKHidalgoCA (2013) The collaborative image of the city: mapping the inequality of urban perception. PLoS One8: e68400. DOI: 10.1371/jour-nal.pone.0068400.
69.
SteinbachRPerkinsCTompsonL, et al. (2015) The effect of reduced street lighting on road casualties and crime in England and Wales: controlled interrupted time series analysis. Journal of Epidemiology & Community Health69(11): 1118–1124. DOI: 10.1136/jech-2015-206012.
70.
Subiza-PérezMVozmedianoLJuanCS (2020) Green and blue settings as providers of mental health ecosystem services: comparing urban beaches and parks and building a predictive model of psychological restoration. Landscape and Urban Planning204: 103926. DOI: 10.1016/j.landurbplan.2020.103926.
71.
SvorayTDormanMShaharG, et al. (2018) Demonstrating the effect of exposure to nature on happy facial expressions via Flickr data: advantages of non-intrusive social network data analyses and geoinformatics methodologies. Journal of Environmental Psychology58: 93–100. DOI: 10.1016/j.jenvp.2018.07.006.
TaylorMSWheelerBWWhiteMP, et al. (2015) Research note: urban street tree density and antidepressant prescription rates-A cross-sectional study in London, UK. Landscape and Urban Planning136: 174–179. DOI: 10.1016/j.landurbplan.2014.12.005.
74.
ThompsonCWRoeJAspinallP, et al. (2012) More green space is linked to less stress in deprived communities: evidence from salivary cortisol patterns. Landscape and Urban Planning105: 221–229. DOI: 10.1016/j.landurbplan.2011.12.015.
75.
United Nations, Department of Economic and Social Affairs, Population Division (2019) World Urbanization Prospects: The 2018 Revision (ST/ESA/SER.A/420). New York: United Nations.
76.
van den BergAEJorgensenAWilsonER (2014) Evaluating restoration in urban green spaces: does setting type make a difference?Landscape and Urban Planning127: 173–181. DOI: 10.1016/j.landurbplan.2014.04.012.
77.
VertCGasconMRanzaniO, et al. (2020) Physical and mental health effects of repeated short walks in a blue space environment: a randomised crossover study. Environmental Research188: 109812. DOI: 10.1016/j.envres.2020.109812.
78.
VojnovicIPearsonAAsikiG, et al. (2019) Handbook of Global Urban Health. Routledge.
79.
WangLHanXHeJ, et al. (2022a) Measuring residents’ perceptions of city streets to inform better street planning through deep learning and space syntax. ISPRS Journal of Photogrammetry and Remote Sensing190: 215–230. DOI: 10.1016/j.isprsjprs.2022.06.011.
80.
WangRBrowningMHEMQinX, et al. (2022b) Visible green space predicts emotion: evidence from social media and street view data. Applied Geography148: 102–803. DOI: 10.1016/j.apgeog.2022.102803.
81.
WangDWangYFuX, et al. (2023) Revealing the spatial co-occurrence patterns of multi-emotions from social media data. Telematics and Informatics84: 102025. DOI: 10.1016/j.tele.2023.102025.
82.
WeiHHauerRJSunY, et al. (2022) Emotional perceptions of people exposed to green and blue spaces in forest parks of cities at rapid urbanization regions of East China. Urban Forestry and Urban Greening78: 127772. DOI: 10.1016/j.ufug.2022.127772.
83.
WhiteMPPahlSWheelerBW, et al. (2016) The ‘Blue Gym’: what can blue space do for you and what can you do for blue space?Journal of the Marine Biological Association of the United Kingdom96: 5–12. DOI: 10.1017/S0025315415002209.
84.
XiangLCaiMRenC, et al. (2021) Modeling pedestrian emotion in high-density cities using visual exposure and machine learning: tracking real-time physiology and psychology in Hong Kong. Building and Environment205: 108273. DOI: 10.1016/j.buildenv.2021.108273.
85.
YaoLXuYZhangB (2019a) Effect of urban function and landscape structure on the urban heat island phenomenon in Beijing, China. Landscape and Ecological Engineering15: 379–390. DOI: 10.1007/s11355-019-00388-5.
86.
YaoYLiangZYuanZ, et al. (2019b) A human-machine adversarial scoring framework for urban perception assessment using street-view images. International Journal of Geographical Information Science33: 2363–2384. DOI: 10.1080/13658816.2019.1643024.
87.
YinJRamanpongJChangJ, et al. (2024) Effects of blue space exposure in urban and natural environments on psychological and physiological responses: a within-subject experiment. Urban Forestry and Urban Greening94: 128271. DOI: 10.1016/j.ufug.2024.128271.
88.
YoshimuraNHiuraT (2017) Demand and supply of cultural ecosystem services: use of geotagged photos to map the aesthetic value of landscapes in Hokkaido. Ecosystem Services24: 68–78. DOI: 10.1016/j.ecoser.2017.02.009.
89.
ZabelskyteGKabischNStasiskieneZ (2022) Patterns of urban green space use applying social media data: a systematic literature review. Land11: 238. DOI: 10.3390/land11020238.
90.
ZavadskasEKBausysRMazonaviciuteI (2019) Safety evaluation methodology of urban public parks by multi-criteria decision making. Landscape and Urban Planning189: 372–381. DOI: 10.1016/j.landurbplan.2019.05.014.
91.
ZhangFZhouBLiuL, et al. (2018) Measuring human perceptions of a large-scale urban region using machine learning. Landscape and Urban Planning180: 148–160. DOI: 10.1016/j.landurbplan.2018.08.020.
92.
ZhangXHanHQiaoL, et al. (2022) Emotional-health-oriented urban design: a novel collaborative deep learning framework for real-time landscape assessment by integrating facial expression recognition and pixel-level semantic segmentation. International Journal of Environmental Research and Public Health19: 13308. DOI: 10.3390/ijerph192013308.
93.
ZhangTWangLZhangY, et al. (2024) Assessing the nonlinear impact of green space exposure on psychological stress perception using machine learning and street view images. Frontiers in Public Health12: 1402536. DOI: 10.3389/fpubh.2024.1402536.
94.
ZhaoWTanLNiuS, et al. (2024) Assessing the impact of street visual environment on the emotional well-being of young adults through physiological feedback and deep learning technologies. Buildings14(6): 1730. DOI: 10.3390/buildings14061730.
95.
ZhuJFanY (2018) Daily travel behavior and emotional well-being: effects of trip mode, duration, purpose, and companionship. Transportation Research Part A: Policy and Practice118: 360–373. DOI: 10.1016/j.tra.2018.09.019.
96.
ZouSWangL (2021) Detecting individual abandoned houses from Google Street View: a hierarchical deep learning approach. ISPRS Journal of Photogrammetry and Remote Sensing175: 298–310. DOI: 10.1016/j.isprsjprs.2021.03.020.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
