Sudden disruptions, such as the COVID-19 pandemic, can reshape multiple dimensions of everyday urban life by affecting social interactions, mobility patterns, and the use of urban spaces. Previous research efforts trying to understand the consequences for citizens relied on top-down proxies such as mobility traces, transit usage, or aggregate economic indicators. While these capture where and how much people move, they do not create new insights into how different domains of everyday urban life are perceived, discussed, and coped with over time.
This study investigates how geotagged Twitter data can be used to classify posts into predefined urban functional categories and analyze their temporal and spatial dynamics in New York City from 2018 to 2022. The research focuses on five key domains: Transportation, Retail Activity, Cultural/Social Activity, Healthcare, and Work/Remote Work. To classify content related to these categories, a methodological workflow combining Wikipedia-derived keyword filtering with BERTopic-based modeling was developed.
Temporal and spatial analyses of category-related activity reveal distinct patterns of intensifications and declines, particularly within Transportation and Cultural/Social Activity. Deviations from long-term baseline shares illustrate localized disruptions and partial recoveries in these categories, while domains with sparse representation, such as Healthcare and Work/Remote Work, display fragmented patterns that limit interpretability.
The study demonstrates the potential and constraints of using geotagged social media as a complementary source for understanding urban behavioral change. While representation biases and data sparsity remain challenges, the developed workflow offers a means to trace spatial and temporal shifts in selected aspects of urban life, particularly during large-scale events such as the COVID-19 pandemic.
| [1] |
Almatar MG, Alazmi HS, Li L, Fox EA. Applying GIS and Text Mining Methods to Twitter Data to Explore the Spatiotemporal Patterns of Topics of Interest in Kuwait. Isprs International Journal of Geo-Information, 2020, 9(12702 https://www.mdpi.com/2220-9964/9/12/702
|
| [2] |
Arifi D, Resch B, Santillana M, Guan WW, Knoblauch S, Lautenbach S, Jaenisch T, Morales I, Havas C. Geosocial media’s early warning capabilities across US county-level political clusters: Observational study. JMIR Infodemiology, 2025, 5(1 e58539
|
| [3] |
Arifi, D., Resch, B., Santillana, M., Knoblauch, S., Lautenbach, S., Jaenisch, T., & Morales, I. (2025). How politics affect pandemic forecasting: spatio-temporal early warning capabilities of different geo-social media topics in the context of state-level political leaning [Original Research]. Frontiers in Public Health, 13. https://doi.org/10.3389/fpubh.2025.1618347
|
| [4] |
Bandarin F, Ciciotti E, Cremaschi M, Madera G, Perulli P, Shendrikova D. After Covid-19: A survey on the prospects for cities. City, Culture and Society, 2021, 25 100400
|
| [5] |
Batty M, Bettencourt LM, Kirley M. Understanding coupled urban-natural dynamics as the key to sustainability: The example of the Galapagos. Urban Galapagos: Transition to sustainability in complex adaptive systems, 2018Springer, 23-41
|
| [6] |
Batty M, Clifton J, Tyler P, Wan L. The post-Covid city. Cambridge Journal of Regions, Economy and Society, 2022, 15(3): 447-457
|
| [7] |
Bettencourt LMA. The origins of scaling in cities. Science, 2013, 340(6139): 1438-1441
|
| [8] |
Bettencourt, L., Lobo, J., & Youn, H. (2013). The hypothesis of urban scaling: formalization, implications and challenges. arXiv. https://arxiv.org/abs/1301.5919
|
| [9] |
Biuk-Aghai, R. P., & Ng, K. K. (2014). A method for automated document classification using Wikipedia-derived weighted keywords. In 2014 International Conference on Data and Software Engineering (ICODSE), https://doi.org/10.1109/ICODSE.2014.7062484
|
| [10] |
Blei DM, Ng AY, Jordan MI. Latent dirichlet allocation. Journal of Machine Learning Research, 2003, 3(Jan): 993-1022
|
| [11] |
Buehler R, Pucher J, White P, Currie G. Public transport and the COVID-19 pandemic: A comparative analysis of trends and policies in Great Britain, Germany, the USA, Canada, and Australia. Transportation Research Part a, Policy and Practice, 2025, 199 104549
|
| [12] |
Campello, R. J. G. B., Moulavi, D., & Sander, J. (2013). Density-Based Clustering Based on Hierarchical Density Estimates. In J. Pei, V. S. Tseng, L. Cao, H. Motoda, & G. Xu, Advances in Knowledge Discovery and Data Mining Berlin, Heidelberg.
|
| [13] |
Campello RJGB, Moulavi D, Zimek A, Sander J. Hierarchical Density Estimates for Data Clustering, Visualization, and Outlier Detection. ACM Transactions on Knowledge Discovery from Data, 2015, 10(1): 5
|
| [14] |
Chen Y, Zhang H, Liu R, Ye Z, Lin J. Experimental explorations on short text topic mining between LDA and NMF based schemes. Knowledge-Based Systems, 2019, 163: 1-13
|
| [15] |
Conneau, A., Khandelwal, K., Goyal, N., Chaudhary, V., Wenzek, G., Guzmán, F., Grave, E., Ott, M., Zettlemoyer, L., & Stoyanov, V. (2019). Unsupervised cross-lingual representation learning at scale. arXiv. https://arxiv.org/abs/1911.02116
|
| [16] |
Crivellari A, Resch B. Investigating functional consistency of mobility-related urban zones via motion-driven embedding vectors and local POI-type distributions. Computational Urban Science, 2022, 2(1): 19
|
| [17] |
Crooks A, Pfoser D, Jenkins A, Croitoru A, Stefanidis A, Smith D, Karagiorgou S, Efentakis A, Lamprianidis G. Crowdsourcing urban form and function. International Journal of Geographical Information Science, 2015, 29(5): 720-741
|
| [22] |
Cuomo, A. M. (2021). Governor Cuomo Announces COVID-19 Restrictions Lifted as 70% of Adult New Yorkers Have Received First Dose of COVID-19 Vaccine. https://www.governor.ny.gov/news/governor-cuomo-announces-covid-19-restrictions-lifted-70-adult-new-yorkers-have-received-first
|
| [23] |
de Albuquerque JP, Herfort B, Brenning A, Zipf A. A geographic approach for combining social media and authoritative data towards identifying useful information for disaster management. International Journal of Geographical Information Science, 2015, 29(4): 667-689
|
| [24] |
De Sabbata S, Bennett K, Gardner Z. Towards a study of everyday geographic information: Bringing the everyday into view. Environment and Planning b: Urban Analytics and City Science, 2023
|
| [25] |
Department of Finance (DOF). (2025). Storefronts Reported Vacant or Not. Retrieved September 2025 from https://data.cityofnewyork.us/City-Government/Storefronts-Reported-Vacant-or-Not/92iy-9c3n/about_data
|
| [26] |
Egger, R., & Yu, J. (2022). A Topic Modeling Comparison Between LDA, NMF, Top2Vec, and BERTopic to Demystify Twitter Posts [Methods]. Frontiers in Sociology, 7. https://doi.org/10.3389/fsoc.2022.886498
|
| [27] |
Feng Y, Zhou W. Work from home during the COVID-19 pandemic: An observational study based on a large geo-tagged COVID-19 Twitter dataset (UsaGeoCov19). Information Processing & Management, 2022, 59(2 102820
|
| [28] |
Ferrara E, Varol O, Davis C, Menczer F, Flammini A. The rise of social bots. Communications of the ACM, 2016, 59(7): 96-104
|
| [29] |
Florida R, Rodríguez-Pose A, Storper M. Critical commentary: Cities in a post-COVID world. Urban Studies, 2021, 60(8): 1509-1531
|
| [30] |
Forouhar A, Chapple K, Pokharel R, Allen J. Transit-driven resilience: Unraveling post-COVID-19 urban recovery dynamics. Journal of Transport Geography, 2025, 128 104327
|
| [31] |
Frias-Martinez, V., Soto, V., Hohwald, H., & Frias-Martinez, E. (2012). Characterizing urban landscapes using geolocated tweets. In 2012 International Conference on Privacy, Security, Risk and Trust and 2012 International Conference on Social Computing, https://doi.org/10.1109/SocialCom-PASSAT.2012.19
|
| [32] |
Gabrilovich, E., & Markovitch, S. (2007). Computing semantic relatedness using Wikipedia-based explicit semantic analysis Proceedings of the 20th international joint conference on Artifical intelligence, Hyderabad, India.
|
| [33] |
Glaeser EL. Reflections on the post-Covid city. Cambridge Journal of Regions, Economy and Society, 2022, 15(3): 747-755
|
| [34] |
Grootendorst, M. (2022). BERTopic: Neural topic modeling with a class-based TF-IDF procedure. arXiv. https://arxiv.org/abs/2203.05794
|
| [35] |
Guo Y, Barnes S, Jia Q. Mining meaning from online ratings and reviews: Tourist satisfaction analysis using latent dirichlet allocation. Tourism Management, 2016, 59: 467-483
|
| [36] |
Hanny D, Arifi D, Knoblauch S, Resch B, Lautenbach S, Zipf A, de Aragão Rocha AA. An explainable GeoAI approach for the multimodal analysis of urban human dynamics: A case study for the COVID-19 pandemic in Rio de Janeiro. Computational Urban Science, 2025, 5(1 13
|
| [37] |
Harris, J. E. (2022). Failure of Concentric Regulatory Zones to Halt the Spread of COVID-19 in South Brooklyn, New York: October-November 2020. medRxiv, 2021.2011.2018.21266493. https://doi.org/10.1101/2021.11.18.21266493
|
| [38] |
Huang X, Li Z, Jiang Y, Li X, Porter D. Twitter reveals human mobility dynamics during the COVID-19 pandemic. PLoS ONE, 2020, 15(11 e0241957
|
| [39] |
Huang J-H, Floyd MF, Tateosian LG, Aaron Hipp J. Exploring public values through Twitter data associated with urban parks pre- and post- COVID-19. Landscape and Urban Planning, 2022, 227 104517
|
| [40] |
Ignaccolo C, Wibisono K, Sutto MP, Plunz RA. Tweeting during the pandemic in New York City: Unveiling the evolving sentiment landscape of NYC through a spatiotemporal analysis of geolocated tweets. Journal of Urban Technology, 2024, 31(3): 3-28
|
| [41] |
Jiang Y, Huang X, Li Z. Spatiotemporal patterns of human mobility and its association with land use types during COVID-19 in New York City. ISPRS International Journal of Geo-Information, 2021, 10(5 344
|
| [42] |
Jiang, N., Crooks, A. T., Kavak, H., & Wang, W. (2023). Leveraging newspapers to understand urban issues: A longitudinal analysis of urban shrinkage in Detroit. Environment and Planning B: Urban Analytics and City Science, 23998083231204695. https://doi.org/10.1177/23998083231204695
|
| [43] |
Joachims, T. (1997). A Probabilistic Analysis of the Rocchio Algorithm with TFIDF for Text Categorization Proceedings of the Fourteenth International Conference on Machine Learning,
|
| [44] |
Jurdak R, Zhao K, Liu J, AbouJaoude M, Cameron M, Newth D. Understanding human mobility from Twitter. PLoS ONE, 2015, 10(7 e0131469
|
| [45] |
Kontokosta CE, Freeman L, Lai Y. Up-and-Coming or Down-and-Out? Social Media Popularity as an Indicator of Neighborhood Change. Journal of Planning Education and Research, 2024, 44(2): 662-673
|
| [46] |
Understanding pre- and post-COVID urbanKovacs-Györi, A., Ristea, A., Kolcsar, R., Resch, B., Crivellari, A., & Blaschke, T. (2018). Beyond Spatial Proximity—Classifying Parks and Their Visitors in London Based on Spatiotemporal and Sentiment Analysis of Twitter Data. Isprs International Journal of Geo-Information, 378(9)26. https://doi.org/10.3390/ijgi7090378.
|
| [47] |
Kozlowska A, Steinnocher K. Urban activity detection using geo-located Twitter data. GI_Forum Journal for Geographic Information Science, 2020, 1: 15-31
|
| [48] |
Lansley G, Longley PA. The geography of Twitter topics in London. Computers, Environment and Urban Systems, 2016, 58: 85-96
|
| [49] |
Li X, Xu M, Zeng W, Tse YK, Chan HK. Exploring customer concerns on service quality under the COVID-19 crisis: A social media analytics study from the retail industry. Journal of Retailing and Consumer Services, 2023, 70 103157
|
| [50] |
Liao Y, Yeh S, Gil J. Feasibility of estimating travel demand using geolocations of social media data. Transportation, 2022, 49(1): 137-161
|
| [51] |
McCorriston, J., Jurgens, D., & Ruths, D. (2015). Organizations are users too: Characterizing and detecting the presence of organizations on twitter. Proceedings of the international aaai conference on web and social media
|
| [52] |
McInnes, L., Healy, J., & Melville, J. (2018). Umap: Uniform manifold approximation and projection for dimension reduction. arXiv. https://arxiv.org/abs/1802.03426
|
| [53] |
Megahed NA, Abdel-Kader RF. Smart cities after COVID-19: Building a conceptual framework through a multidisciplinary perspective. Scientific African, 2022, 17 e01374
|
| [54] |
Miller HJ, Goodchild MF. Data-driven geography. GeoJournal, 2015, 80(4): 449-461
|
| [55] |
Nagarkar, P., Khan, A., Raikar, S., & Zantye, A. (2020). Twitter Data Mining for Targeted Marketing. 2020 Second International Conference on Inventive Research in Computing Applications (ICIRCA),
|
| [56] |
Niu H, Silva EA. Crowdsourced data mining for urban activity: Review of data sources, applications, and methods. Journal of Urban Planning and Development, 2020, 146(2 04020007
|
| [57] |
Niu H, Silva EA. Understanding temporal and spatial patterns of urban activities across demographic groups through geotagged social media data. Computers, Environment and Urban Systems, 2023, 100 101934
|
| [58] |
Niu H, Seraphim AP, Morgado P, Miranda B, Silva EA. Mapping urban emotion from geotagged social media data: Age, gender and spatial heterogeneity. Applied Geography, 2025, 185 103768
|
| [59] |
NYC Office of Technology & Innovation. (2022a). Ferry Landings. Retrieved September 2025 from https://services6.arcgis.com/yG5s3afENB5iO9fj/arcgis/rest/services/FerryLandings_View/FeatureServer
|
| [60] |
NYC Office of Technology & Innovation. (2022b). Railroad 2022. Retrieved September 2025 from https://services6.arcgis.com/yG5s3afENB5iO9fj/arcgis/rest/services/Railroad_2022/FeatureServer
|
| [61] |
NYC Office of Technology & Innovation. (2024a). Facility Database (DCP). Retrieved September 2025 from https://services6.arcgis.com/yG5s3afENB5iO9fj/arcgis/rest/services/FacDB/FeatureServer
|
| [62] |
NYC Office of Technology & Innovation. (2024b). Park 2022. Retrieved September 2025 from https://services6.arcgis.com/yG5s3afENB5iO9fj/arcgis/rest/services/Park_2022/FeatureServer
|
| [64] |
NYC Office of Technology & Innovation. (2025b). Subway Station. Retrieved September 2025 from https://services6.arcgis.com/yG5s3afENB5iO9fj/arcgis/rest/services/SubwayStation_view/FeatureServer
|
| [65] |
Qiang D, McKenzie G. Navigating the post-pandemic urban landscape: Disparities in transportation recovery & regional insights from New York City. Computers, Environment and Urban Systems, 2024, 110 102111
|
| [66] |
Rajput, A. A., Li, Q., Gao, X., & Mostafavi, A. (2022). Revealing Critical Characteristics of Mobility Patterns in New York City During the Onset of COVID-19 Pandemic [Original Research]. Frontiers in Built Environment, 7. https://doi.org/10.3389/fbuil.2021.654409
|
| [67] |
Rao F, Han SS, Pan R. Planning for resilient central-city shopping districts in the post-COVID era: An explanatory case study of the Hoddle Grid in Melbourne. Cambridge Journal of Regions, Economy and Society, 2022, 15(3): 575-596
|
| [68] |
Rath S, Chow JYJ. Worldwide city transport typology prediction with sentence-BERT based supervised learning via Wikipedia. Transportation Research Part c: Emerging Technologies, 2022, 139 103661
|
| [69] |
Resch B, Britter R, Ratti CRassia ST, Pardalos PM. Live urbanism – towards SENSEable cities and beyond. Sustainable environmental design in architecture: Impacts on health, 2012Springer New York, 175-184
|
| [70] |
Resch B, Summa A, Zeile P, Strube M. Citizen-centric urban planning through extracting emotion information from Twitter in an interdisciplinary space-time-linguistics algorithm. Urban Planning, 2016, 1(2): 114-127
|
| [71] |
Resch B, Usländer F, Havas C. Combining machine-learning topic models and spatiotemporal analysis of social media data for disaster footprint and damage assessment. Cartography and Geographic Information Science, 2018, 45(4): 362-376
|
| [72] |
Reuschke D, Long J, Bennett N. Locating creativity in the city using Twitter data. Environment and Planning b: Urban Analytics and City Science, 2021, 48(9): 2607-2622
|
| [73] |
Richardson, L. (2024). Beautiful Soup Documentation. Retrieved November 2024 from https://www.crummy.com/software/BeautifulSoup/bs4/doc/
|
| [74] |
Serere HN, Resch B, Havas CR. Enhanced geocoding precision for location inference of tweet text using spaCy, Nominatim and Google Maps. A comparative analysis of the influence of data selection. PLoS ONE, 2023, 18(3 e0282942
|
| [75] |
Steiger E, Resch B, Zipf A. Exploration of spatiotemporal and semantic clusters of Twitter data using unsupervised neural networks. International Journal of Geographical Information Science, 2016, 30(9): 1694-1716
|
| [76] |
Umair A, Masciari E. Sentimental and spatial analysis of COVID-19 vaccines tweets. Journal of Intelligent Information Systems, 2023, 60(1): 1-21
|
| [77] |
U.S. Census Bureau. (2020). 2020 TIGER/Line® Shapefiles: ZIP Code Tabulation Areas. Retrieved March 2025 from https://www.census.gov/cgi-bin/geo/shapefiles/index.php?year=2020&layergroup=ZIP%20Code%20Tabulation%20Areas
|
| [78] |
Wu Z, Zhu H, Li G, Cui Z, Huang H, Li J, Chen E, Xu G. An efficient Wikipedia semantic matching approach to text document classification. Information Sciences, 2017, 393: 15-28
|
| [79] |
Xu P, Dredze M, Broniatowski DA. The twitter social mobility index: Measuring social distancing practices with geolocated tweets. Journal of Medical Internet Research, 2020, 22(12 e21499
|
| [80] |
Xue J, Chen J, Hu R, Chen C, Zheng C, Su Y, Zhu T. Twitter Discussions and Emotions About the COVID-19 Pandemic: Machine Learning Approach. Journal of Medical Internet Research, 2020, 22(11 e20550
|
| [81] |
Yang C, Liu T. Social media data in urban design and landscape research: A comprehensive literature review. Land, 2022
|
| [82] |
Zhao H, Mailloux BJ, Cook EM, Culligan PJ. Change of urban park usage as a response to the COVID-19 global pandemic. Scientific Reports, 2023, 13(1 19324
|
| [83] |
Zhong C, Morphet R, Yoshida M. Twitter mobility dynamics during the COVID-19 pandemic: A case study of London. PLoS ONE, 2023, 18(4 e0284902
|
| [84] |
Ziedan A, Brakewood C, Watkins K. Will transit recover? A retrospective study of nationwide ridership in the United States during the COVID-19 pandemic. Journal of Public Transportation, 2023, 25 100046
|
Funding
Austrian Science Fund(10.55776/I5117)
Rights & permissions
The Author(s)
PDF
